Oxygen-deprived underwater zones may not be "dead zones" but clue to early life
23 by gumby | 1 comments on Hacker News.
Thursday, October 1, 2026
Wednesday, September 30, 2026
New top story on Hacker News: Show HN: Parrot – Open-Source Smart Meeting Recorder with Co-Pilot on Mac
Show HN: Parrot – Open-Source Smart Meeting Recorder with Co-Pilot on Mac
10 by turantekin | 3 comments on Hacker News.
Hello Hacker News I am Uygar, I am an entrepreneur from London. I run my businesses on calls everyday, customers, partners and suppliers. And i have a horrible memory i forgot things. So months ago with the help of Claude i have built Parrot. I have designed and coded for my work and what i need. An to be honest worked very well and helped me alot. Parrot records what your mac hears and everything stays in your computer if you use local models, no account, no API calls. There is something called copilot which made my life easier, you can upload your files and when parrot hears that question on the screen recommends the answer. Which i believe very handy. If you want to make it smarter and dont mind cloud you can hook up your Claude API and Deepgram account, that gives super powers to Parrot. You still keep it locally but eventually you need to make API calls. So local or cloud totally up to you. Then after months of thinking i have decided share it as open source and this is my first open source project, so please go easy on me :) No account, no membership, open source and free. Code: https://ift.tt/Ti1JbXj This project made me so excited and really would like to share with you guys so i hope can help you too. Again, i am new so go easy on me and if you have any feedback i would like to hear. Thank you Uygar
10 by turantekin | 3 comments on Hacker News.
Hello Hacker News I am Uygar, I am an entrepreneur from London. I run my businesses on calls everyday, customers, partners and suppliers. And i have a horrible memory i forgot things. So months ago with the help of Claude i have built Parrot. I have designed and coded for my work and what i need. An to be honest worked very well and helped me alot. Parrot records what your mac hears and everything stays in your computer if you use local models, no account, no API calls. There is something called copilot which made my life easier, you can upload your files and when parrot hears that question on the screen recommends the answer. Which i believe very handy. If you want to make it smarter and dont mind cloud you can hook up your Claude API and Deepgram account, that gives super powers to Parrot. You still keep it locally but eventually you need to make API calls. So local or cloud totally up to you. Then after months of thinking i have decided share it as open source and this is my first open source project, so please go easy on me :) No account, no membership, open source and free. Code: https://ift.tt/Ti1JbXj This project made me so excited and really would like to share with you guys so i hope can help you too. Again, i am new so go easy on me and if you have any feedback i would like to hear. Thank you Uygar
Tuesday, September 29, 2026
New top story on Hacker News: Ask HN: What are you reading?
Ask HN: What are you reading?
17 by dan-bailey | 45 comments on Hacker News.
I'm plowing through the Dungeon Crawler Carl series, which is not particularly challenging as sci-fi/LitRPG goes, but entertaining enough. I'm also wrapping up Doctorow's _Enshittification_, and I'm looking for something a little meaty to keep the brain working...
17 by dan-bailey | 45 comments on Hacker News.
I'm plowing through the Dungeon Crawler Carl series, which is not particularly challenging as sci-fi/LitRPG goes, but entertaining enough. I'm also wrapping up Doctorow's _Enshittification_, and I'm looking for something a little meaty to keep the brain working...
Monday, September 28, 2026
Sunday, September 27, 2026
New top story on Hacker News: Oral history of John Chowning, inventor of FM synthesis [video]
Oral history of John Chowning, inventor of FM synthesis [video]
4 by Rochus | 0 comments on Hacker News.
https://ift.tt/tUpBOmn
4 by Rochus | 0 comments on Hacker News.
https://ift.tt/tUpBOmn
Saturday, September 26, 2026
New top story on Hacker News: Show HN: Reladraw – A diagram language where you decide where to place things
Show HN: Reladraw – A diagram language where you decide where to place things
8 by jpwalsh234 | 0 comments on Hacker News.
I love making diagrams to help understand, plan, etc. However, the options are (A) auto-placement languages like Mermaid or Graphviz (which don't let me decide how the diagram looks), or (B) software like Draw.io which are powerful but are very time consuming (and inefficient for agents to manipulate). I wanted to have the benefits of both, where you can define a diagram in a diagram language, but also retain a high degree of control over what the diagram looks like. I also wanted this to work well for humans and agents. On the Github link, there's a playground where you can try it out without installation. There's also instructions for a simple npm install and for installing a skill you can use with Claude or other agents.
8 by jpwalsh234 | 0 comments on Hacker News.
I love making diagrams to help understand, plan, etc. However, the options are (A) auto-placement languages like Mermaid or Graphviz (which don't let me decide how the diagram looks), or (B) software like Draw.io which are powerful but are very time consuming (and inefficient for agents to manipulate). I wanted to have the benefits of both, where you can define a diagram in a diagram language, but also retain a high degree of control over what the diagram looks like. I also wanted this to work well for humans and agents. On the Github link, there's a playground where you can try it out without installation. There's also instructions for a simple npm install and for installing a skill you can use with Claude or other agents.
Friday, September 25, 2026
Thursday, September 24, 2026
Wednesday, September 23, 2026
New top story on Hacker News: Show HN: I built a post-mortem debugger for native Windows x64/x86 crashes
Show HN: I built a post-mortem debugger for native Windows x64/x86 crashes
3 by Loren_SL | 0 comments on Hacker News.
Hello HN! I've spent years debugging Windows crashes with tools that were either friendly but limited (e.g. Visual Studio) or powerful but archaic (e.g. WinDbg). I developed patterns and methods for understanding what was going on, and decided to build it into a much more effective debugging tool called ForensicDbg. I built a modern interface to minimize the friction when debugging. All of the data shown to you is analyzed, interpreted, and presented to you clearly, so you can focus on what matters. Everything is interlinked so you can quickly and intuitivly navigate through the process space. ForensicDbg comes with an MCP server which allows for agenic debugging. The work done to interpret and interlink your data also benefits AI tools. It removes the risk of hallucinations while building a stable foundation for them to work from without spending tokens. If you want to try it out you can sign up and get a free beta license here: https://ift.tt/2FgqP9O
3 by Loren_SL | 0 comments on Hacker News.
Hello HN! I've spent years debugging Windows crashes with tools that were either friendly but limited (e.g. Visual Studio) or powerful but archaic (e.g. WinDbg). I developed patterns and methods for understanding what was going on, and decided to build it into a much more effective debugging tool called ForensicDbg. I built a modern interface to minimize the friction when debugging. All of the data shown to you is analyzed, interpreted, and presented to you clearly, so you can focus on what matters. Everything is interlinked so you can quickly and intuitivly navigate through the process space. ForensicDbg comes with an MCP server which allows for agenic debugging. The work done to interpret and interlink your data also benefits AI tools. It removes the risk of hallucinations while building a stable foundation for them to work from without spending tokens. If you want to try it out you can sign up and get a free beta license here: https://ift.tt/2FgqP9O
Tuesday, September 22, 2026
Monday, September 21, 2026
Sunday, September 20, 2026
Saturday, September 19, 2026
New top story on Hacker News: Show HN: CUA-S1 – A System One Model for Computer Use
Show HN: CUA-S1 – A System One Model for Computer Use
7 by frabonacci | 0 comments on Hacker News.
Hello HN! We're Dillon and Francesco from Cua. We were wondering how many computer use tasks actually need a full general purpose LLM (e.g. gpt-6-astra, claude-opus-5 etc.) to think through all their decisions and steps. Some tasks require thinking about a plan, exploring different paths, recovering from failure. Other tasks are a question of making local decisions, like this value should go in this box, or should I check this box, or this element should be ignored. We wondered how far we could go with a small model trained to only make these kinds of decisions. Our inspiration was Typesafe's Jev and its System One Model framing. This is a nod to the dichotomy between thinking quickly, automatically, and intuitively (system 1) vs. thinking slowly, analytically (system 2), as described by Daniel Kahneman. The interesting question for us was: what happens if you give a model an interface of current context, and a set of possible choices, and you ask it to return a probability for each choice? This kind of model does not generate output token by token like most LLMs do, but rather scores the options you give it, which you can check, trust, and use to drive your app's behavior. CUA-S1 is our answer for narrow, specialized decision models for computer use. Our first release is CUA-S1-FORMS. We built this from ideas and code in jevlike, and then trained a second model just to handle form interactions. It has 706k parameters, and the original checkpoint is 2.8 MB. The first training iteration took less than 30 minutes on synthetic data. Given a set of structured elements and values extracted from a document, it predicts whether to use the given value, CHECK, CLICK, or SKIP for each element. It does not predict new values for text fields, and does not consider screenshots. Element decisions are scored together, and your code can order the actions, and Cua Driver will execute them one at a time. A first evaluation of this specialist vs. hosted Jev on our form task: - For the whole decision set: 99.7% correct vs 83.6%. - For the subset of steps that require an action: 100% correct vs 96%. - For the subset of steps that are just leaving already-filled fields alone: 100% correct vs 74%. The specialist was trained specifically for this task and convention (just press skip for already filled boxes), while hosted Jev has not been fine-tuned for it, so this is an experiment in scoped specialization. We measured 7-9 ms to score a form locally vs. 260-280 ms per call to hosted Jev including network latency, though those samples measure different things and are not end-to-end form completion times. Our interest here is in the space between a brittle script and a general agent loop. The content and layout of form fields vary enough that scripts get unwieldy, but the set of available decisions can remain narrow and well scoped. We want to explore the possibility of a general agent encountering something novel, and passing well understood decisions over to specialists like this. That is a direction we are looking into. The current release is for forms only. We're open sourced the synthetic data generation, training, evaluation, and Driver integration under libs/cua-s1 with an MIT license. Comments welcome! Especially if you are building computer-use agents and have run into a recurring decision that is too variable to script but is too narrow to call another LLM for.
7 by frabonacci | 0 comments on Hacker News.
Hello HN! We're Dillon and Francesco from Cua. We were wondering how many computer use tasks actually need a full general purpose LLM (e.g. gpt-6-astra, claude-opus-5 etc.) to think through all their decisions and steps. Some tasks require thinking about a plan, exploring different paths, recovering from failure. Other tasks are a question of making local decisions, like this value should go in this box, or should I check this box, or this element should be ignored. We wondered how far we could go with a small model trained to only make these kinds of decisions. Our inspiration was Typesafe's Jev and its System One Model framing. This is a nod to the dichotomy between thinking quickly, automatically, and intuitively (system 1) vs. thinking slowly, analytically (system 2), as described by Daniel Kahneman. The interesting question for us was: what happens if you give a model an interface of current context, and a set of possible choices, and you ask it to return a probability for each choice? This kind of model does not generate output token by token like most LLMs do, but rather scores the options you give it, which you can check, trust, and use to drive your app's behavior. CUA-S1 is our answer for narrow, specialized decision models for computer use. Our first release is CUA-S1-FORMS. We built this from ideas and code in jevlike, and then trained a second model just to handle form interactions. It has 706k parameters, and the original checkpoint is 2.8 MB. The first training iteration took less than 30 minutes on synthetic data. Given a set of structured elements and values extracted from a document, it predicts whether to use the given value, CHECK, CLICK, or SKIP for each element. It does not predict new values for text fields, and does not consider screenshots. Element decisions are scored together, and your code can order the actions, and Cua Driver will execute them one at a time. A first evaluation of this specialist vs. hosted Jev on our form task: - For the whole decision set: 99.7% correct vs 83.6%. - For the subset of steps that require an action: 100% correct vs 96%. - For the subset of steps that are just leaving already-filled fields alone: 100% correct vs 74%. The specialist was trained specifically for this task and convention (just press skip for already filled boxes), while hosted Jev has not been fine-tuned for it, so this is an experiment in scoped specialization. We measured 7-9 ms to score a form locally vs. 260-280 ms per call to hosted Jev including network latency, though those samples measure different things and are not end-to-end form completion times. Our interest here is in the space between a brittle script and a general agent loop. The content and layout of form fields vary enough that scripts get unwieldy, but the set of available decisions can remain narrow and well scoped. We want to explore the possibility of a general agent encountering something novel, and passing well understood decisions over to specialists like this. That is a direction we are looking into. The current release is for forms only. We're open sourced the synthetic data generation, training, evaluation, and Driver integration under libs/cua-s1 with an MIT license. Comments welcome! Especially if you are building computer-use agents and have run into a recurring decision that is too variable to script but is too narrow to call another LLM for.
Friday, September 18, 2026
New top story on Hacker News: The first new cat species discovered in 100 years
The first new cat species discovered in 100 years
41 by ohjeez | 10 comments on Hacker News.
https://ift.tt/eYwV9T6
41 by ohjeez | 10 comments on Hacker News.
https://ift.tt/eYwV9T6
New top story on Hacker News: Show HN: Ax-check.com – Can agents use your product?
Show HN: Ax-check.com – Can agents use your product?
12 by 0x63_Problems | 12 comments on Hacker News.
I'm the co-founder of Gauge, and I built ax-check.com to quickly test how well coding agents can onboard to your product. You'll get a scorecard, specific suggested fixes, and three full coding sessions that show how agents read your site and use your product. I built this because similar checks were too noisy. Most suggested obscure technical changes that don't actually make a difference in agent experience (or AX, hence ax-check.com). This check starts by using DeepSeek 4.1 Flash to try to find key information about your product, starting from the homepage. In actual agent traffic data, we've seen that the key pages are the homepage, llms.txt, pricing, and the docs site (by traffic volume, and by influence), so we focus on those and ignore the rest. We also find that content negotiation for Markdown is legitimately helpful for agents to complete tasks faster and find what they're looking for, so the scan tests that your key pages can serve Markdown. The other key piece is that we run actual coding agents in sandboxes, and have them try to onboard to your product. You can see the full trace and watch it happen live (we kick it off fresh when you enter a new site). We surface interesting findings like hallucinated URLs, inaccurate docs instructions, or product confusion. It also detects whether the agents could complete a fully working onboarding autonomously, without being blocked by a login wall. This is still controversial, but I think finding ways to let agents safely onboard autonomously is going to be table stakes within a year for developer tools in particular. The whole site is agent-friendly itself! You can generally just talk to your coding agent about ax-check.com and it can do the rest. Would really appreciate any feedback to make this useful.
12 by 0x63_Problems | 12 comments on Hacker News.
I'm the co-founder of Gauge, and I built ax-check.com to quickly test how well coding agents can onboard to your product. You'll get a scorecard, specific suggested fixes, and three full coding sessions that show how agents read your site and use your product. I built this because similar checks were too noisy. Most suggested obscure technical changes that don't actually make a difference in agent experience (or AX, hence ax-check.com). This check starts by using DeepSeek 4.1 Flash to try to find key information about your product, starting from the homepage. In actual agent traffic data, we've seen that the key pages are the homepage, llms.txt, pricing, and the docs site (by traffic volume, and by influence), so we focus on those and ignore the rest. We also find that content negotiation for Markdown is legitimately helpful for agents to complete tasks faster and find what they're looking for, so the scan tests that your key pages can serve Markdown. The other key piece is that we run actual coding agents in sandboxes, and have them try to onboard to your product. You can see the full trace and watch it happen live (we kick it off fresh when you enter a new site). We surface interesting findings like hallucinated URLs, inaccurate docs instructions, or product confusion. It also detects whether the agents could complete a fully working onboarding autonomously, without being blocked by a login wall. This is still controversial, but I think finding ways to let agents safely onboard autonomously is going to be table stakes within a year for developer tools in particular. The whole site is agent-friendly itself! You can generally just talk to your coding agent about ax-check.com and it can do the rest. Would really appreciate any feedback to make this useful.
Thursday, September 17, 2026
New top story on Hacker News: Show HN: Craigslist for agent skills, curated by a human
Show HN: Craigslist for agent skills, curated by a human
7 by skeptrune | 3 comments on Hacker News.
hey, i'm nick (@skeptrune on X). i have been using ai for a lot of things i'm not an expert in and thought it would be nice to try and buy paid skills for helping it accomplish those tasks more efficiently. for example, redlining contracts, creating ai generated videos, different website designs, and more. curious to see if this resonates with folks here. i figure a more engineering'y audience that's ai coding-agent forward would have similar problems to what inspired me to make this
7 by skeptrune | 3 comments on Hacker News.
hey, i'm nick (@skeptrune on X). i have been using ai for a lot of things i'm not an expert in and thought it would be nice to try and buy paid skills for helping it accomplish those tasks more efficiently. for example, redlining contracts, creating ai generated videos, different website designs, and more. curious to see if this resonates with folks here. i figure a more engineering'y audience that's ai coding-agent forward would have similar problems to what inspired me to make this
Wednesday, September 16, 2026
Tuesday, September 15, 2026
Monday, September 14, 2026
Sunday, September 13, 2026
Saturday, September 12, 2026
New top story on Hacker News: An open letter to Dario: if you mean it, open the weights
An open letter to Dario: if you mean it, open the weights
124 by routelastresort | 35 comments on Hacker News.
124 by routelastresort | 35 comments on Hacker News.
Friday, September 11, 2026
Thursday, September 10, 2026
Wednesday, September 9, 2026
Tuesday, September 8, 2026
Monday, September 7, 2026
Sunday, September 6, 2026
Saturday, September 5, 2026
Friday, September 4, 2026
Thursday, September 3, 2026
Wednesday, September 2, 2026
New top story on Hacker News: Google avoids a breakup of its ad tech business
Google avoids a breakup of its ad tech business
66 by donohoe | 22 comments on Hacker News.
https://ift.tt/vdwWmIn https://ift.tt/JUscy5L...
66 by donohoe | 22 comments on Hacker News.
https://ift.tt/vdwWmIn https://ift.tt/JUscy5L...
Tuesday, September 1, 2026
New top story on Hacker News: Ask HN: Who wants to be hired? (September 2026)
Ask HN: Who wants to be hired? (September 2026)
37 by whoishiring | 164 comments on Hacker News.
Share your information if you are looking for work. Please use this format: Location: Remote: Willing to relocate: Technologies: Résumé/CV: Email: Please only post if you are personally looking for work. Agencies, recruiters, job boards, and so on, are off topic here. Readers: please only email these addresses to discuss work opportunities. Searchers: try https://ift.tt/j8z0E9s , https://ift.tt/IXMiS9m .
37 by whoishiring | 164 comments on Hacker News.
Share your information if you are looking for work. Please use this format: Location: Remote: Willing to relocate: Technologies: Résumé/CV: Email: Please only post if you are personally looking for work. Agencies, recruiters, job boards, and so on, are off topic here. Readers: please only email these addresses to discuss work opportunities. Searchers: try https://ift.tt/j8z0E9s , https://ift.tt/IXMiS9m .
Monday, August 31, 2026
Sunday, August 30, 2026
Saturday, August 29, 2026
Friday, August 28, 2026
Thursday, August 27, 2026
Wednesday, August 26, 2026
Tuesday, August 25, 2026
New top story on Hacker News: OpenAI Jalapeño: Better than Nvidia Blackwell
OpenAI Jalapeño: Better than Nvidia Blackwell
81 by bmulholland | 21 comments on Hacker News.
https://ift.tt/3Gdm26y... , https://ift.tt/7IJ1kOe
81 by bmulholland | 21 comments on Hacker News.
https://ift.tt/3Gdm26y... , https://ift.tt/7IJ1kOe
Monday, August 24, 2026
Sunday, August 23, 2026
Saturday, August 22, 2026
Friday, August 21, 2026
New top story on Hacker News: Felony charges for citizen deleting phone data at US Border
Felony charges for citizen deleting phone data at US Border
90 by floathub | 150 comments on Hacker News.
https://ift.tt/F3pA4GD https://www.youtube.com/watch?v=_2rokxux5cU
90 by floathub | 150 comments on Hacker News.
https://ift.tt/F3pA4GD https://www.youtube.com/watch?v=_2rokxux5cU
Thursday, August 20, 2026
Wednesday, August 19, 2026
New top story on Hacker News: A revisit of remote Spectre attacks on Cloudflare Workers
A revisit of remote Spectre attacks on Cloudflare Workers
6 by albertpedersen | 0 comments on Hacker News.
Paper: https://ift.tt/yMdHvTq ("Remote-Timer-as-a-Service: Efficient Microarchitectural Leakage in the Cloud with Remote Timers")
6 by albertpedersen | 0 comments on Hacker News.
Paper: https://ift.tt/yMdHvTq ("Remote-Timer-as-a-Service: Efficient Microarchitectural Leakage in the Cloud with Remote Timers")
Tuesday, August 18, 2026
Monday, August 17, 2026
Sunday, August 16, 2026
New top story on Hacker News: Tell HN: Cloudflare silently injects its analytics when you switch nameservers
Tell HN: Cloudflare silently injects its analytics when you switch nameservers
28 by stagas | 2 comments on Hacker News.
A few hours ago I switched my nameservers to Cloudflare in order to enable R2 bucket serving through my own subdomain, and I found out that it silently had injected a JS analytics snippet in my HTML-only JS-free site textlog.cc — I had to go to the Analytics dashboard, Add the site to the analytics and then disable the snippet. I find this approach entirely invasive, you should opt-in to features like that not have to opt-out. Just a warning out there to folks who might not be aware of this.
28 by stagas | 2 comments on Hacker News.
A few hours ago I switched my nameservers to Cloudflare in order to enable R2 bucket serving through my own subdomain, and I found out that it silently had injected a JS analytics snippet in my HTML-only JS-free site textlog.cc — I had to go to the Analytics dashboard, Add the site to the analytics and then disable the snippet. I find this approach entirely invasive, you should opt-in to features like that not have to opt-out. Just a warning out there to folks who might not be aware of this.
Saturday, August 15, 2026
Friday, August 14, 2026
Thursday, August 13, 2026
Wednesday, August 12, 2026
Tuesday, August 11, 2026
Monday, August 10, 2026
New top story on Hacker News: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
17 by HenryNdubuaku | 2 comments on Hacker News.
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges 300-700 on sub-$200 phones such as the Samsung A-Series. On the tool call and mobile device use benchmarks, Needle 2 trades wins with closest small models like LFM2.5 230M and Apple Foundation Model, at 5x to 70x smaller, both at f16 vs Needle 2 at 2bit. Needle is based on Simple Attention Networks from our paper ( https://ift.tt/dZ9ahyk ). Edge AI has lately meant Macs and PCs, but that is just 1.5 billion of over 21 billion connected IoT devices in the world today, and in emerging markets most phones ship under $200, no NPU, cheap GPUs. These include budget phones, Raspberry Pis, microcontrollers, wearables, small robots like Reachy Mini, and connected home devices. A conventional transformer of Needle's width and depth spends 164 MFLOPs per token, and even one squeezed down to Needle's parameter count spends 87, Needle spends 70. Even on a high-end phone, an always-on assistant lives inside a power budget; every MFLOP is milliwatt-hours, and Needle spends 7x to 85x fewer of them per token than the smallest performant LLMs. More about the architecture in the link. When we structure intelligence for consumer devices as functions with typed parameters, the only hard part is mapping a messy sentence onto them; which function, with which values. Our research found that when framed that way, the problem needs no world knowledge and no open-ended prose, which is why 45M parameters suffice. Needle 2 expands to structured extraction where the schema can be passed in-place of tools and the model returns structured output. You can use Needle as a text-classification model with an enum field, as a summarization model by providing a schema that extracts key fields, everything but free-range decode. Every product has its own tool vocabulary and fine-tuning needle helps it achieve frontier-level performance on custom tasks, so using the python package ( https://ift.tt/Fc6e7zA ), Needle can be fine-tuned Needle on a Mac/PC in minutes to a few hours, with automated data-generation pipeline, just pass a couple samples. Nonetheless, every response carries a learned confidence score based our Cactus Hybrid technique. If above your threshold, act, below it, escalate to the cloud or bigger model. Combining Needle 2 with a private DeepSeek-v4-Flash deployment works particularly well for enterprise-level tasks at barely any cost, we can help with this setup. We have put a lot of thoughts into Needle 2 but might still be missing quite a lot, please use the playground in the provided link to test Needle and share your thoughts, always appreciated!
17 by HenryNdubuaku | 2 comments on Hacker News.
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges 300-700 on sub-$200 phones such as the Samsung A-Series. On the tool call and mobile device use benchmarks, Needle 2 trades wins with closest small models like LFM2.5 230M and Apple Foundation Model, at 5x to 70x smaller, both at f16 vs Needle 2 at 2bit. Needle is based on Simple Attention Networks from our paper ( https://ift.tt/dZ9ahyk ). Edge AI has lately meant Macs and PCs, but that is just 1.5 billion of over 21 billion connected IoT devices in the world today, and in emerging markets most phones ship under $200, no NPU, cheap GPUs. These include budget phones, Raspberry Pis, microcontrollers, wearables, small robots like Reachy Mini, and connected home devices. A conventional transformer of Needle's width and depth spends 164 MFLOPs per token, and even one squeezed down to Needle's parameter count spends 87, Needle spends 70. Even on a high-end phone, an always-on assistant lives inside a power budget; every MFLOP is milliwatt-hours, and Needle spends 7x to 85x fewer of them per token than the smallest performant LLMs. More about the architecture in the link. When we structure intelligence for consumer devices as functions with typed parameters, the only hard part is mapping a messy sentence onto them; which function, with which values. Our research found that when framed that way, the problem needs no world knowledge and no open-ended prose, which is why 45M parameters suffice. Needle 2 expands to structured extraction where the schema can be passed in-place of tools and the model returns structured output. You can use Needle as a text-classification model with an enum field, as a summarization model by providing a schema that extracts key fields, everything but free-range decode. Every product has its own tool vocabulary and fine-tuning needle helps it achieve frontier-level performance on custom tasks, so using the python package ( https://ift.tt/Fc6e7zA ), Needle can be fine-tuned Needle on a Mac/PC in minutes to a few hours, with automated data-generation pipeline, just pass a couple samples. Nonetheless, every response carries a learned confidence score based our Cactus Hybrid technique. If above your threshold, act, below it, escalate to the cloud or bigger model. Combining Needle 2 with a private DeepSeek-v4-Flash deployment works particularly well for enterprise-level tasks at barely any cost, we can help with this setup. We have put a lot of thoughts into Needle 2 but might still be missing quite a lot, please use the playground in the provided link to test Needle and share your thoughts, always appreciated!
Sunday, August 9, 2026
Saturday, August 8, 2026
Friday, August 7, 2026
Thursday, August 6, 2026
Wednesday, August 5, 2026
Tuesday, August 4, 2026
Monday, August 3, 2026
Sunday, August 2, 2026
Saturday, August 1, 2026
Friday, July 31, 2026
Thursday, July 30, 2026
Wednesday, July 29, 2026
Tuesday, July 28, 2026
Monday, July 27, 2026
Sunday, July 26, 2026
Saturday, July 25, 2026
New top story on Hacker News: Show HN: Brolly, a plain-text weather forecast site
Show HN: Brolly, a plain-text weather forecast site
26 by jsax | 6 comments on Hacker News.
The UK MET office recently redesigned their site, adding a lot of additional whitespace, scrolling, and animations. This significantly reduced its usability for me, and left me wanting an ‘at a glance’ weather site. I made https://brolly.sh , a minimalist, plain text weather forecasting site. You can use it to view weather from around the world, with: 7 day forecast; Previous day log (so you can confirm it definitely was cooler / hotter / wetter / drier yesterday!); Hourly rain, wind, temperature, conditions; Hourly UV, air quality and pollen, including pollen type specific forecasts within the EU / UK; Location search and last 5 locations; Location specific units. I mostly made the site for myself, if anyone else also benefits from it that’s an added advantage. You can check out the weather in York, UK at https://ift.tt/8mAEpFo , or search for a location at https://brolly.sh The site is deliberately styled as a single long scrollable column, to work on mobile phones. You can view it on desktop too, there's just a lot of horizontal padding. I naturally took a lot of inspiration from plaintextsports.com. Despite not being a sports fan, I love its aesthetic. But, you'll hopefully see that this site isn't a rip off, and has its own deliberate look and feel. Visualisations are really important to showing information at a glance. I spent a lot of time designing the different visualisations and making them work with only characters. My favourite is the hourly heat map used for pollen count. It's also frustrating to have an interactive site, where you can't share a page with a friend and have them see what you're seeing. To solve this, all page state (i.e. location, selected day, expanded / collapsed sections), is stored in the URL. You can share or bookmark the specific view, and know that you'll always be able to come back to it. The site uses PocketBase. It’s written in Go and plain HTML/JavaScript/CSS. All pages are backend rendered, with light JavaScript to handle re-loading content without page jumps when using interactive features like next / previous day navigation. Weather forecasts are fetched from open-meteo.com, which has a very generous free tier. However, I also built a custom LRU cache on top of PocketBase’s SQLite DB to cache forecasts for 5 minutes, and avoid putting unnecessary pressure on the open-meteo API.
26 by jsax | 6 comments on Hacker News.
The UK MET office recently redesigned their site, adding a lot of additional whitespace, scrolling, and animations. This significantly reduced its usability for me, and left me wanting an ‘at a glance’ weather site. I made https://brolly.sh , a minimalist, plain text weather forecasting site. You can use it to view weather from around the world, with: 7 day forecast; Previous day log (so you can confirm it definitely was cooler / hotter / wetter / drier yesterday!); Hourly rain, wind, temperature, conditions; Hourly UV, air quality and pollen, including pollen type specific forecasts within the EU / UK; Location search and last 5 locations; Location specific units. I mostly made the site for myself, if anyone else also benefits from it that’s an added advantage. You can check out the weather in York, UK at https://ift.tt/8mAEpFo , or search for a location at https://brolly.sh The site is deliberately styled as a single long scrollable column, to work on mobile phones. You can view it on desktop too, there's just a lot of horizontal padding. I naturally took a lot of inspiration from plaintextsports.com. Despite not being a sports fan, I love its aesthetic. But, you'll hopefully see that this site isn't a rip off, and has its own deliberate look and feel. Visualisations are really important to showing information at a glance. I spent a lot of time designing the different visualisations and making them work with only characters. My favourite is the hourly heat map used for pollen count. It's also frustrating to have an interactive site, where you can't share a page with a friend and have them see what you're seeing. To solve this, all page state (i.e. location, selected day, expanded / collapsed sections), is stored in the URL. You can share or bookmark the specific view, and know that you'll always be able to come back to it. The site uses PocketBase. It’s written in Go and plain HTML/JavaScript/CSS. All pages are backend rendered, with light JavaScript to handle re-loading content without page jumps when using interactive features like next / previous day navigation. Weather forecasts are fetched from open-meteo.com, which has a very generous free tier. However, I also built a custom LRU cache on top of PocketBase’s SQLite DB to cache forecasts for 5 minutes, and avoid putting unnecessary pressure on the open-meteo API.
New top story on Hacker News: Show HN: I made some transistor animations
Show HN: I made some transistor animations
17 by stunningllama | 1 comments on Hacker News.
Hi HN, I made some animations of the most important kinds of transistors using my semiconductor simulation, details of which are on the page. I tried to make the visuals as realistic as possible while also aiming for clarity. If you want to go beyond the charge carriers and look at, for example, the electric field, you can do so in the simulation software. The desktop software also has less common devices like IBGTs and SCRs that have similar animations. The last thread about my software was posted here about a year ago: https://ift.tt/7anQwEi
17 by stunningllama | 1 comments on Hacker News.
Hi HN, I made some animations of the most important kinds of transistors using my semiconductor simulation, details of which are on the page. I tried to make the visuals as realistic as possible while also aiming for clarity. If you want to go beyond the charge carriers and look at, for example, the electric field, you can do so in the simulation software. The desktop software also has less common devices like IBGTs and SCRs that have similar animations. The last thread about my software was posted here about a year ago: https://ift.tt/7anQwEi
Friday, July 24, 2026
Thursday, July 23, 2026
Wednesday, July 22, 2026
Tuesday, July 21, 2026
New top story on Hacker News: Show HN: DocCharm – The help center that keeps itself up to date
Show HN: DocCharm – The help center that keeps itself up to date
4 by yakshaving_jgt | 0 comments on Hacker News.
Hello HN! We were finding it too much work to keep our Zendesk help center up to date as our product kept changing, so I built DocCharm — it keeps a help center up to date automatically by watching PRs as they land in your GitHub repository. It suggests updates (with AI) to existing articles, or drafts entirely new ones if nothing appropriate exists yet. Everything goes into a review queue first, so a human always checks (and can optionally edit) before anything publishes. In practice this has proven to be a pretty slick workflow (in my opinion anyway, but not only!). We’ve been using it at my main job for a while now and it’s a big time saver. It’s also gaining some traction with other companies in the same investor portfolio. My sales process so far has been high-touch outbound. This probably won’t scale in the long run, but I’m hoping to learn as much as I can by nurturing all of the initial relationships. If you run a business with a help center that’s drifting out of date, email me and I’ll comp your first couple of months. Email is in my HN profile. Both Zendesk and Mintlify help centers can already be automatically imported into DocCharm. If you use a different help center, let me know and I’ll get it automatically imported one way or another. I've also implemented some support for theming, so you can keep your own branding. The tech is essentially the same that I use for most of my work (and it's not a differentiator, but we're all tech-curious here): - Haskell/Yesod - NixOS - SQLite with Litestream (db per tenant; backed up on both Hetzner and Cloudflare; encrypted) - Sentry for error reporting - Stripe for billing - Healthchecks.io as a dead man’s switch - Prometheus and Grafana for telemetry - Resend for transactional email There's plenty still to do on the roadmap, but this is already working nicely and providing value as is. I'm not building in the open, though what I prioritise will naturally be heavily guided by the needs of the earliest users. WDYT?
4 by yakshaving_jgt | 0 comments on Hacker News.
Hello HN! We were finding it too much work to keep our Zendesk help center up to date as our product kept changing, so I built DocCharm — it keeps a help center up to date automatically by watching PRs as they land in your GitHub repository. It suggests updates (with AI) to existing articles, or drafts entirely new ones if nothing appropriate exists yet. Everything goes into a review queue first, so a human always checks (and can optionally edit) before anything publishes. In practice this has proven to be a pretty slick workflow (in my opinion anyway, but not only!). We’ve been using it at my main job for a while now and it’s a big time saver. It’s also gaining some traction with other companies in the same investor portfolio. My sales process so far has been high-touch outbound. This probably won’t scale in the long run, but I’m hoping to learn as much as I can by nurturing all of the initial relationships. If you run a business with a help center that’s drifting out of date, email me and I’ll comp your first couple of months. Email is in my HN profile. Both Zendesk and Mintlify help centers can already be automatically imported into DocCharm. If you use a different help center, let me know and I’ll get it automatically imported one way or another. I've also implemented some support for theming, so you can keep your own branding. The tech is essentially the same that I use for most of my work (and it's not a differentiator, but we're all tech-curious here): - Haskell/Yesod - NixOS - SQLite with Litestream (db per tenant; backed up on both Hetzner and Cloudflare; encrypted) - Sentry for error reporting - Stripe for billing - Healthchecks.io as a dead man’s switch - Prometheus and Grafana for telemetry - Resend for transactional email There's plenty still to do on the roadmap, but this is already working nicely and providing value as is. I'm not building in the open, though what I prioritise will naturally be heavily guided by the needs of the earliest users. WDYT?
Monday, July 20, 2026
Sunday, July 19, 2026
Saturday, July 18, 2026
Friday, July 17, 2026
Thursday, July 16, 2026
Wednesday, July 15, 2026
Tuesday, July 14, 2026
Monday, July 13, 2026
Sunday, July 12, 2026
Saturday, July 11, 2026
Friday, July 10, 2026
Thursday, July 9, 2026
New top story on Hacker News: Show HN: Abralo – Free, easy way to run several Claude Code agents in one window
Show HN: Abralo – Free, easy way to run several Claude Code agents in one window
15 by cwbuilds | 3 comments on Hacker News.
Hi guys, I've been using Claude Code for almost everything lately. Have given one an email account so it can research business leads, draft emails, fact-check them and clear them with me before sending (works really well by the way). I also tend to have a few Claude Code agents running at any one time for coding. I used to create a split terminal to manage them from there, but found working in the terminal all day pretty depressing and, more importantly, found it hard to follow Claude Code's process and see which agents needed my immediate attention. I tried Anthropic's VS Code Claude Code extension and it had a great UI (more info on Claude Code's process and easier to read), but it crashed my PC when I ran more than 3 and I couldn't watch multiple agents in parallel (had to constantly switch between them). So I built a lightweight Tauri desktop app which lets you run multiple Claude Code agents in one window alongside each other. It's easier to read the output and see which agents need your attention than a terminal. Have been using this all day everyday instead of an IDE and have obsessed over every detail to make sure it's easy-to-use, but also lightweight and fast (so you can manage multiple agents without your PC crashing). There are some nice features like better usage alerts for when you're going to hit your 5-hour and weekly limits (with sparklines to show when usage peaked, and which agents are the most token-intensive). It's free to use (you just need to log in with your existing Claude Code account) for up to 4 agents simultaneously. This app doesn't store your Claude Code account details and doesn't store any of your interactions with Claude Code. They remain between you and Anthropic. It's compatible with Windows, MacOS and 64-bit Linux. Would really appreciate any feedback, so if you have any thoughts, issues or suggestions please let me know. Thanks, Chris
15 by cwbuilds | 3 comments on Hacker News.
Hi guys, I've been using Claude Code for almost everything lately. Have given one an email account so it can research business leads, draft emails, fact-check them and clear them with me before sending (works really well by the way). I also tend to have a few Claude Code agents running at any one time for coding. I used to create a split terminal to manage them from there, but found working in the terminal all day pretty depressing and, more importantly, found it hard to follow Claude Code's process and see which agents needed my immediate attention. I tried Anthropic's VS Code Claude Code extension and it had a great UI (more info on Claude Code's process and easier to read), but it crashed my PC when I ran more than 3 and I couldn't watch multiple agents in parallel (had to constantly switch between them). So I built a lightweight Tauri desktop app which lets you run multiple Claude Code agents in one window alongside each other. It's easier to read the output and see which agents need your attention than a terminal. Have been using this all day everyday instead of an IDE and have obsessed over every detail to make sure it's easy-to-use, but also lightweight and fast (so you can manage multiple agents without your PC crashing). There are some nice features like better usage alerts for when you're going to hit your 5-hour and weekly limits (with sparklines to show when usage peaked, and which agents are the most token-intensive). It's free to use (you just need to log in with your existing Claude Code account) for up to 4 agents simultaneously. This app doesn't store your Claude Code account details and doesn't store any of your interactions with Claude Code. They remain between you and Anthropic. It's compatible with Windows, MacOS and 64-bit Linux. Would really appreciate any feedback, so if you have any thoughts, issues or suggestions please let me know. Thanks, Chris
Wednesday, July 8, 2026
Tuesday, July 7, 2026
Monday, July 6, 2026
New top story on Hacker News: Januscape: Guest-to-Host Escape in KVM/x86 [CVE-2026-53359]
Januscape: Guest-to-Host Escape in KVM/x86 [CVE-2026-53359]
16 by Imustaskforhelp | 3 comments on Hacker News.
16 by Imustaskforhelp | 3 comments on Hacker News.
Sunday, July 5, 2026
Saturday, July 4, 2026
Friday, July 3, 2026
New top story on Hacker News: Show HN: Bramble – Local-first password manager
Show HN: Bramble – Local-first password manager
89 by MegagramEnjoyer | 18 comments on Hacker News.
I'm currently working on Bramble, an open source password manager with P2P cross-device sync. Initially I released the Chrome extension, but recently I also published the Android app and iOS is pending Apple's approval. Besides that, the latest version also includes passkey storage for all platforms! About Bramble: It aims to be as feature-rich as all popular and a replacement for cloud-based providers. I don't think we need to store our data in the cloud and be at the whims of companies raising their prices every year. There's always a breach and then we find out that some fields aren't encrypted, metadata is visible, and so on. I'm frustrated with this and the increasing lack of transparency during these breaches. The P2P sync in Bramble uses a Nostr relay (which can be self-hosted) to keep your devices in sync. The relay just introduces the devices to each other; the data then flows directly over WebRTC, so there's no vault server and no cloud copy of your passwords anywhere. What leaves your device is end-to-end encrypted and your devices authenticate each other directly, so a snooping or MITM relay gets practically nothing. Crypto is all done in Rust so I can control exactly how key material lives and dies in memory (secrets get zeroed out, no GB leaving copies lying around). In Chromium it's a wasm module, on mobile it's native builds bridged over via uniffi. Android app: I'm still deciding whether to publish the app on Play store or simply provide the signed APK which users can sideload. Reason for that is Google's plan to lock down Android and take away ownership from its users. Read more about it here: https://ift.tt/DuSB94W The app uses no Play APIs whatsoever and runs perfectly on GrapheneOS, where I actually did all my testing. Questions, feedback, feature requests - all welcome! TL;DR: I dislike private-equity and venture funded companies messing with our security, so I created my own Password Manager which is local-first, free, open source and as transparent as it gets.
89 by MegagramEnjoyer | 18 comments on Hacker News.
I'm currently working on Bramble, an open source password manager with P2P cross-device sync. Initially I released the Chrome extension, but recently I also published the Android app and iOS is pending Apple's approval. Besides that, the latest version also includes passkey storage for all platforms! About Bramble: It aims to be as feature-rich as all popular and a replacement for cloud-based providers. I don't think we need to store our data in the cloud and be at the whims of companies raising their prices every year. There's always a breach and then we find out that some fields aren't encrypted, metadata is visible, and so on. I'm frustrated with this and the increasing lack of transparency during these breaches. The P2P sync in Bramble uses a Nostr relay (which can be self-hosted) to keep your devices in sync. The relay just introduces the devices to each other; the data then flows directly over WebRTC, so there's no vault server and no cloud copy of your passwords anywhere. What leaves your device is end-to-end encrypted and your devices authenticate each other directly, so a snooping or MITM relay gets practically nothing. Crypto is all done in Rust so I can control exactly how key material lives and dies in memory (secrets get zeroed out, no GB leaving copies lying around). In Chromium it's a wasm module, on mobile it's native builds bridged over via uniffi. Android app: I'm still deciding whether to publish the app on Play store or simply provide the signed APK which users can sideload. Reason for that is Google's plan to lock down Android and take away ownership from its users. Read more about it here: https://ift.tt/DuSB94W The app uses no Play APIs whatsoever and runs perfectly on GrapheneOS, where I actually did all my testing. Questions, feedback, feature requests - all welcome! TL;DR: I dislike private-equity and venture funded companies messing with our security, so I created my own Password Manager which is local-first, free, open source and as transparent as it gets.
Thursday, July 2, 2026
Wednesday, July 1, 2026
New top story on Hacker News: A complete ClickHouse OLAP engine, compiled to WebAssembly
A complete ClickHouse OLAP engine, compiled to WebAssembly
15 by porridgeraisin | 0 comments on Hacker News.
15 by porridgeraisin | 0 comments on Hacker News.
Tuesday, June 30, 2026
Monday, June 29, 2026
Sunday, June 28, 2026
Saturday, June 27, 2026
Friday, June 26, 2026
Thursday, June 25, 2026
Wednesday, June 24, 2026
New top story on Hacker News: Show HN: LookAway, a Mac break reminder that knows when not to interrupt
Show HN: LookAway, a Mac break reminder that knows when not to interrupt
7 by _kush | 0 comments on Hacker News.
Hello, I'm Kushagra and I am the indie developer behind LookAway (I've posted about it earlier but it has received quite a lot of updates since the last time so I am posting it again). LookAway is a native break reminder for macOS that doesn't interrupt. I built it because I work from home and I spend a lot of time in front of my screens. It's very easy for me to get lost in the flow and I can end up sitting for hours. Due to this, I started facing issues like eye strain and back pain by the end of the day. The solution to this was simply taking enough breaks throughout the day. But remembering to take breaks was difficult, especially when I was in the flow. I tried some reminder apps but the problem with those was that they always interrupted me at the worst moments. So I ended up not using them. LookAway is designed not to interrupt. It gives enough heads up before a break so that you're not caught off-guard. It's also context-aware and it automatically pauses when you go into a meeting, start watching a video, record screen, and much more. It even waits for you to finish typing or dictating when a break is due. One thing worth mentioning is the free iOS counterpart LookAway Mirror. When your Mac goes on a break, your iOS devices can also mirror the same break so you don't end up scrolling your phone screen during the Mac break. I've spent a lot of time in making LookAway the least annoying break reminder app and I would love to know your thoughts. It's a native Swift app so it doesn't take much resources (150MB RAM and <1% CPU when idle). It's available to download from the website (lookaway.com), Setapp, and the App Store. Thank you!
7 by _kush | 0 comments on Hacker News.
Hello, I'm Kushagra and I am the indie developer behind LookAway (I've posted about it earlier but it has received quite a lot of updates since the last time so I am posting it again). LookAway is a native break reminder for macOS that doesn't interrupt. I built it because I work from home and I spend a lot of time in front of my screens. It's very easy for me to get lost in the flow and I can end up sitting for hours. Due to this, I started facing issues like eye strain and back pain by the end of the day. The solution to this was simply taking enough breaks throughout the day. But remembering to take breaks was difficult, especially when I was in the flow. I tried some reminder apps but the problem with those was that they always interrupted me at the worst moments. So I ended up not using them. LookAway is designed not to interrupt. It gives enough heads up before a break so that you're not caught off-guard. It's also context-aware and it automatically pauses when you go into a meeting, start watching a video, record screen, and much more. It even waits for you to finish typing or dictating when a break is due. One thing worth mentioning is the free iOS counterpart LookAway Mirror. When your Mac goes on a break, your iOS devices can also mirror the same break so you don't end up scrolling your phone screen during the Mac break. I've spent a lot of time in making LookAway the least annoying break reminder app and I would love to know your thoughts. It's a native Swift app so it doesn't take much resources (150MB RAM and <1% CPU when idle). It's available to download from the website (lookaway.com), Setapp, and the App Store. Thank you!
Tuesday, June 23, 2026
Monday, June 22, 2026
Sunday, June 21, 2026
Saturday, June 20, 2026
Friday, June 19, 2026
New top story on Hacker News: Companies rein in AI usage as costs strain budgets
Companies rein in AI usage as costs strain budgets
29 by fandorin | 10 comments on Hacker News.
https://ift.tt/L6BEWcf
29 by fandorin | 10 comments on Hacker News.
https://ift.tt/L6BEWcf
Thursday, June 18, 2026
New top story on Hacker News: Agentic Resource Discovery Specification
Agentic Resource Discovery Specification
16 by damick | 4 comments on Hacker News.
https://ift.tt/ncq3NdT...
16 by damick | 4 comments on Hacker News.
https://ift.tt/ncq3NdT...
New top story on Hacker News: Ask HN: What is the job market like?
Ask HN: What is the job market like?
31 by gardnr | 23 comments on Hacker News.
We've all heard about layoffs; what are people's actual lived experiences when it comes to the recent changes in the job market?
31 by gardnr | 23 comments on Hacker News.
We've all heard about layoffs; what are people's actual lived experiences when it comes to the recent changes in the job market?
Wednesday, June 17, 2026
New top story on Hacker News: The hacker sent by Anthropic to calm the government's nerves about AI safety
The hacker sent by Anthropic to calm the government's nerves about AI safety
40 by Brajeshwar | 27 comments on Hacker News.
Readable: https://ift.tt/UmNfWry...
40 by Brajeshwar | 27 comments on Hacker News.
Readable: https://ift.tt/UmNfWry...
Tuesday, June 16, 2026
New top story on Hacker News: Show HN: Pen and paper resource development game with an emergent world
Show HN: Pen and paper resource development game with an emergent world
9 by jhylands | 0 comments on Hacker News.
I've been working for a while on trying to curate a game that has the emergence of procedurally generated computer games but that can be played with only pen and paper. Here I present the best version I've been able to come up with that is simple and emergent. I've really enjoyed being able to engage with this sort of game while not feeling like my brain in rotting. I recon my numeracy improves while playing it.
9 by jhylands | 0 comments on Hacker News.
I've been working for a while on trying to curate a game that has the emergence of procedurally generated computer games but that can be played with only pen and paper. Here I present the best version I've been able to come up with that is simple and emergent. I've really enjoyed being able to engage with this sort of game while not feeling like my brain in rotting. I recon my numeracy improves while playing it.
Monday, June 15, 2026
Sunday, June 14, 2026
New top story on Hacker News: Show HN: Trace – Offline Mac meeting transcripts you can flag mid-call
Show HN: Trace – Offline Mac meeting transcripts you can flag mid-call
5 by AG342 | 2 comments on Hacker News.
I'm the developer of Trace, a non-intrusive, shortcut-driven Mac app that records and transcribes your meetings on-device. I know, another meeting transcription app. Please bear with me though, I'm confident that this is at least a little novel. I primarily built Trace for myself. I'd been using MacWhisper, but there was enough fiddling before each call that I'd forget to start it and walk out of an hour-long meeting with nothing written down. So the things I cared about most were that it's quick to activate and stays out of the way. You activate Trace by pressing a global shortcut (configurable), which reveals a small bar at the bottom of your screen (there's also a keystroke and/or option to hide it entirely if you'd rather not see it at all). As I was building it I wanted to bake in a couple of workflows I'd wished for in other transcription apps. 1. Mid-meeting you can press another global shortcut to mark a "key moment" and type a note. The note shows up in the resulting transcript inline at that timestamp. I wanted to add this because I kept catching myself thinking "wait, that bit matters" in meetings and reaching to jot it down in a separate app like Obsidian, which I then needed to add context to, which took me out of the meeting. I use it all the time. If I paste the transcript into an LLM afterwards (which I find myself doing more and more these days) the important moments are flagged so it doesn't gloss over them. This is more noticeable in longer meetings with lots of topics. 2. With another keyboard shortcut you can summon a rough live recap (subtitles, basically) to quickly recap what's just been said. Trace uses standard macOS microphone and system recording APIs to capture both sides of the conversation as two separate tracks and then runs the system side through on-device diarization to identify speakers. Right now we only label them as "Speaker 1", "Speaker 2", etc but there are plans for speaker labelling in the future. You can also show a "live recap" as the call is happening to review what someone just said. All transcription models run on your machine. To be clear though, Trace doesn't do any of the summarising itself, it just produces a markdown transcript, so if you want summaries then you need to pass the output to an AI. The app is sandboxed and your audio/transcripts are never uploaded anywhere - they just exist as audio files and markdown on disk. The only network call Trace is required to make is on the first run to download the speech and speaker models (around 500MB) from Hugging Face, and after that it can be used fully offline. If enabled, a Google Calendar integration can auto-name sessions but that needs a network connection. The app is £9.99 on the macOS App Store. I've been using it every day for months now and I'm super happy with how it's improved my workflow. Feedback very welcome.
5 by AG342 | 2 comments on Hacker News.
I'm the developer of Trace, a non-intrusive, shortcut-driven Mac app that records and transcribes your meetings on-device. I know, another meeting transcription app. Please bear with me though, I'm confident that this is at least a little novel. I primarily built Trace for myself. I'd been using MacWhisper, but there was enough fiddling before each call that I'd forget to start it and walk out of an hour-long meeting with nothing written down. So the things I cared about most were that it's quick to activate and stays out of the way. You activate Trace by pressing a global shortcut (configurable), which reveals a small bar at the bottom of your screen (there's also a keystroke and/or option to hide it entirely if you'd rather not see it at all). As I was building it I wanted to bake in a couple of workflows I'd wished for in other transcription apps. 1. Mid-meeting you can press another global shortcut to mark a "key moment" and type a note. The note shows up in the resulting transcript inline at that timestamp. I wanted to add this because I kept catching myself thinking "wait, that bit matters" in meetings and reaching to jot it down in a separate app like Obsidian, which I then needed to add context to, which took me out of the meeting. I use it all the time. If I paste the transcript into an LLM afterwards (which I find myself doing more and more these days) the important moments are flagged so it doesn't gloss over them. This is more noticeable in longer meetings with lots of topics. 2. With another keyboard shortcut you can summon a rough live recap (subtitles, basically) to quickly recap what's just been said. Trace uses standard macOS microphone and system recording APIs to capture both sides of the conversation as two separate tracks and then runs the system side through on-device diarization to identify speakers. Right now we only label them as "Speaker 1", "Speaker 2", etc but there are plans for speaker labelling in the future. You can also show a "live recap" as the call is happening to review what someone just said. All transcription models run on your machine. To be clear though, Trace doesn't do any of the summarising itself, it just produces a markdown transcript, so if you want summaries then you need to pass the output to an AI. The app is sandboxed and your audio/transcripts are never uploaded anywhere - they just exist as audio files and markdown on disk. The only network call Trace is required to make is on the first run to download the speech and speaker models (around 500MB) from Hugging Face, and after that it can be used fully offline. If enabled, a Google Calendar integration can auto-name sessions but that needs a network connection. The app is £9.99 on the macOS App Store. I've been using it every day for months now and I'm super happy with how it's improved my workflow. Feedback very welcome.
Saturday, June 13, 2026
Friday, June 12, 2026
Thursday, June 11, 2026
New top story on Hacker News: Show HN: I built a Red Flag Warning zone-check tool for the East Bay in 48h
Show HN: I built a Red Flag Warning zone-check tool for the East Bay in 48h
6 by vedant28t | 0 comments on Hacker News.
Hey HN. I'm a high schooler in Fremont, CA. Tuesday morning I got a county-wide AC Alert text telling everyone in Alameda County to prepare a go-bag for an East Bay Hills Red Flag Warning that starts tonight at 11 PM. The text went to ~half a million phones. The actual NWS warning polygon only covers East Bay Hills (NWS zone CAZ515). Most people who got the text don't need a go-bag tonight. Some in the hills don't realize how close they are. So I built this tool - https://ift.tt/tQPonpa mit licensed public github - https://ift.tt/ZYH8C95 It does a few things - tells people if they are in the flagged zone, and also provides a way to check if a buddy is in flagged zone and send them a text. Everything without installing an app. I heard back from Oakland Firesafe Council director about a gap in my understanding (and the tool). To my surprise, and through feedback, I realized that you cannot assume that only the flagged area is at risk. Adjacent areas are at risk too! Fires do not follow zone boundaries! I fixed the tool. I built this in 48 hours to close that specific gap: type your address, get a yes/no on whether the NWS polygon covers it, your Genasys evacuation zone, tonight's wind + humidity at your point, a plain-English action checklist, a per-school decision view for East Bay districts, and a one-tap iMessage buddy-check template for a hill-neighbor at 10:30 PM.
6 by vedant28t | 0 comments on Hacker News.
Hey HN. I'm a high schooler in Fremont, CA. Tuesday morning I got a county-wide AC Alert text telling everyone in Alameda County to prepare a go-bag for an East Bay Hills Red Flag Warning that starts tonight at 11 PM. The text went to ~half a million phones. The actual NWS warning polygon only covers East Bay Hills (NWS zone CAZ515). Most people who got the text don't need a go-bag tonight. Some in the hills don't realize how close they are. So I built this tool - https://ift.tt/tQPonpa mit licensed public github - https://ift.tt/ZYH8C95 It does a few things - tells people if they are in the flagged zone, and also provides a way to check if a buddy is in flagged zone and send them a text. Everything without installing an app. I heard back from Oakland Firesafe Council director about a gap in my understanding (and the tool). To my surprise, and through feedback, I realized that you cannot assume that only the flagged area is at risk. Adjacent areas are at risk too! Fires do not follow zone boundaries! I fixed the tool. I built this in 48 hours to close that specific gap: type your address, get a yes/no on whether the NWS polygon covers it, your Genasys evacuation zone, tonight's wind + humidity at your point, a plain-English action checklist, a per-school decision view for East Bay districts, and a one-tap iMessage buddy-check template for a hill-neighbor at 10:30 PM.
Wednesday, June 10, 2026
Tuesday, June 9, 2026
New top story on Hacker News: Show HN: Transit-format (JSON/MessagePack) reader/writer in C
Show HN: Transit-format (JSON/MessagePack) reader/writer in C
3 by delaguardo | 0 comments on Hacker News.
Transit.c is an addition to the set of libraries to support transit data interchange format written in C11. It supports full 0.8 specification of cognitect's transit-format: JSON, JSON-Verbose and MessagePack encodings, all ground and extension types, compression via keys caching, extensibility via custom tag handlers.
3 by delaguardo | 0 comments on Hacker News.
Transit.c is an addition to the set of libraries to support transit data interchange format written in C11. It supports full 0.8 specification of cognitect's transit-format: JSON, JSON-Verbose and MessagePack encodings, all ground and extension types, compression via keys caching, extensibility via custom tag handlers.
Monday, June 8, 2026
Sunday, June 7, 2026
Saturday, June 6, 2026
Friday, June 5, 2026
New top story on Hacker News: Inside FAISS: Billion-Scale Similarity Search
Inside FAISS: Billion-Scale Similarity Search
10 by tohms | 0 comments on Hacker News.
Author here. I wrote this as a visual companion to the 2017 FAISS paper ( https://ift.tt/LjKG6lS ), focused on the parts I found hardest to grok from text alone. The article covers a subset of what FAISS does, with the paper as the source of truth. NSG, FastScan, IMI are not covered here, they'll get their own articles. I'd be especially interested in feedback on: - the IVFPQ / IVFADC explanation, particularly the LUT reuse argument - whether the GPU part captures enough of the actual complexity Happy to answer questions.
10 by tohms | 0 comments on Hacker News.
Author here. I wrote this as a visual companion to the 2017 FAISS paper ( https://ift.tt/LjKG6lS ), focused on the parts I found hardest to grok from text alone. The article covers a subset of what FAISS does, with the paper as the source of truth. NSG, FastScan, IMI are not covered here, they'll get their own articles. I'd be especially interested in feedback on: - the IVFPQ / IVFADC explanation, particularly the LUT reuse argument - whether the GPU part captures enough of the actual complexity Happy to answer questions.
Thursday, June 4, 2026
New top story on Hacker News: Show HN: Cost.dev (YC W21) – making agents cost-aware and cheaper to call
Show HN: Cost.dev (YC W21) – making agents cost-aware and cheaper to call
6 by akh | 0 comments on Hacker News.
We launched Infracost on HN five years ago ( https://ift.tt/e5GYSl4 ) where our CLI generated cost estimates for infra-as-code, e.g. "this Terraform PR adds $400/mo". The idea was to shift cloud costs (FinOps) left, so engineers get visibility of costs before deployment and make better decisions. Earlier this year we started seeing agent traffic in our logs and it looked like coding agents were calling our CLI. But that CLI wasn't designed with coding agents in mind. We went down a philosophical rabbit hole to see if a CLI is even needed anymore given that Claude, Copilot et al. already follow best practices. Ultimately we decided to create a new CLI from the ground up with coding agents in mind for two reasons: 1. We optimized the CLI for agent callers and cut Claude's output token usage by up to 79% and API cost by up to 67% versus a bare-Claude baseline. We wrote a blog documenting our lessons on optimizing user token usage when designing a CLI, e.g. using predicate flags so the agent doesn't compose jq | python | wc pipelines, output format that strips JSON's redundant field names. The blog is here: https://ift.tt/sdYEKcN... 2. With cloud costs, precision matters. Telling a coding agent "make this Terraform cost-optimized" can be expensive and lossy. You burn tokens loading code and policy context into every conversation. Your agent could make up a price and you wouldn't know because it's difficult to verify that across the ~10M price points that AWS, Azure and Google have. The CLI runs static analysis on the code, uses the latest prices from cloud vendors, and passes that context to the coding agent. So that's what we're launching today - Cost.dev: https://cost.dev/ . - It runs locally. Your code never leaves your machine, you get a fast feedback loop, and you're not burning API calls per character when you want to fetch prices. - The CLI does the deterministic work. Fetching price points, scanning the code, validating fixes. The coding agent does the natural-language part. You don't have to trust the LLM to remember the rules, and can verify it called the right CLI command. - It provides a consistent rule layer across every tool you use. Get cost estimates in your IDE and your coding agent with a single install. We support Claude Code, GitHub Copilot, Cursor, Windsurf, OpenAI Codex, Gemini CLI, as well as IDEs like VS Code and JetBrains Before we keep building more in that direction, I want to sanity-check with HN: is "agents writing IaC in prod" actually a thing yet, or am I betting on a future that's still a year out? I know software developers are using coding agents heavily, but are platform/infra folks doing that for prod too? Also, if you have any feedback on Cost.dev, I'd love to hear it!
6 by akh | 0 comments on Hacker News.
We launched Infracost on HN five years ago ( https://ift.tt/e5GYSl4 ) where our CLI generated cost estimates for infra-as-code, e.g. "this Terraform PR adds $400/mo". The idea was to shift cloud costs (FinOps) left, so engineers get visibility of costs before deployment and make better decisions. Earlier this year we started seeing agent traffic in our logs and it looked like coding agents were calling our CLI. But that CLI wasn't designed with coding agents in mind. We went down a philosophical rabbit hole to see if a CLI is even needed anymore given that Claude, Copilot et al. already follow best practices. Ultimately we decided to create a new CLI from the ground up with coding agents in mind for two reasons: 1. We optimized the CLI for agent callers and cut Claude's output token usage by up to 79% and API cost by up to 67% versus a bare-Claude baseline. We wrote a blog documenting our lessons on optimizing user token usage when designing a CLI, e.g. using predicate flags so the agent doesn't compose jq | python | wc pipelines, output format that strips JSON's redundant field names. The blog is here: https://ift.tt/sdYEKcN... 2. With cloud costs, precision matters. Telling a coding agent "make this Terraform cost-optimized" can be expensive and lossy. You burn tokens loading code and policy context into every conversation. Your agent could make up a price and you wouldn't know because it's difficult to verify that across the ~10M price points that AWS, Azure and Google have. The CLI runs static analysis on the code, uses the latest prices from cloud vendors, and passes that context to the coding agent. So that's what we're launching today - Cost.dev: https://cost.dev/ . - It runs locally. Your code never leaves your machine, you get a fast feedback loop, and you're not burning API calls per character when you want to fetch prices. - The CLI does the deterministic work. Fetching price points, scanning the code, validating fixes. The coding agent does the natural-language part. You don't have to trust the LLM to remember the rules, and can verify it called the right CLI command. - It provides a consistent rule layer across every tool you use. Get cost estimates in your IDE and your coding agent with a single install. We support Claude Code, GitHub Copilot, Cursor, Windsurf, OpenAI Codex, Gemini CLI, as well as IDEs like VS Code and JetBrains Before we keep building more in that direction, I want to sanity-check with HN: is "agents writing IaC in prod" actually a thing yet, or am I betting on a future that's still a year out? I know software developers are using coding agents heavily, but are platform/infra folks doing that for prod too? Also, if you have any feedback on Cost.dev, I'd love to hear it!
Wednesday, June 3, 2026
Tuesday, June 2, 2026
Monday, June 1, 2026
New top story on Hacker News: Florida sues OpenAI and Sam Altman over AI risks
Florida sues OpenAI and Sam Altman over AI risks
14 by cyunker | 2 comments on Hacker News.
https://ift.tt/6w0Tzne... https://ift.tt/ER9ejaD...
14 by cyunker | 2 comments on Hacker News.
https://ift.tt/6w0Tzne... https://ift.tt/ER9ejaD...
Sunday, May 31, 2026
Saturday, May 30, 2026
Friday, May 29, 2026
Thursday, May 28, 2026
Wednesday, May 27, 2026
Tuesday, May 26, 2026
Monday, May 25, 2026
Sunday, May 24, 2026
Saturday, May 23, 2026
New top story on Hacker News: Green card seekers must leave U.S. to apply, Trump administration says
Green card seekers must leave U.S. to apply, Trump administration says
100 by tlhunter | 386 comments on Hacker News.
https://ift.tt/U6wsuHd... https://ift.tt/dnNViYB... [pdf] https://twitter.com/DHSgov/status/2057817233200418837 , https://ift.tt/KHWZAwT https://ift.tt/1uIt8Un https://ift.tt/A8QhNlR... , https://ift.tt/68ZV0f5
100 by tlhunter | 386 comments on Hacker News.
https://ift.tt/U6wsuHd... https://ift.tt/dnNViYB... [pdf] https://twitter.com/DHSgov/status/2057817233200418837 , https://ift.tt/KHWZAwT https://ift.tt/1uIt8Un https://ift.tt/A8QhNlR... , https://ift.tt/68ZV0f5
Friday, May 22, 2026
Thursday, May 21, 2026
Wednesday, May 20, 2026
Tuesday, May 19, 2026
Monday, May 18, 2026
Sunday, May 17, 2026
Saturday, May 16, 2026
Friday, May 15, 2026
Thursday, May 14, 2026
Wednesday, May 13, 2026
Tuesday, May 12, 2026
New top story on Hacker News: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
10 by HenryNdubuaku | 1 comments on Hacker News.
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention is the right primitive for this, and FFN parameters are wasted at this scale. Simple Attention Networks: the entire model is just attention and gating, no MLPs anywhere. Needle is an experimental run for single-shot function calling for consumer devices (phones, watches, glasses...). Training: - Pretrained on 200B tokens across 16 TPU v6e (27 hours) - Post-trained on 2B tokens of synthesized function-calling data (45 minutes) - Dataset synthesized via Gemini with 15 tool categories (timers, messaging, navigation, smart home, etc.) You can test it right now and finetune on your Mac/PC: https://ift.tt/cLsNU6K The full writeup on the architecture is here: https://ift.tt/J81foIv... We found that the "no FFN" finding generalizes beyond function calling to any task where the model has access to external structured knowledge (RAG, tool use, retrieval-augmented generation). The model doesn't need to memorize facts in FFN weights if the facts are provided in the input. Experimental results to published. While it beats FunctionGemma-270M, Qwen-0.6B, Granite-350M, LFM2.5-350M on single-shot function calling, those models have more scope/capacity and excel in conversational settings. We encourage you to test on your own tools via the playground and finetune accordingly. This is part of our broader work on Cactus ( https://ift.tt/Lsay4TY ), an inference engine built from scratch for mobile, wearables and custom hardware. We wrote about Cactus here previously: https://ift.tt/M2upWRs Everything is MIT licensed. Weights: https://ift.tt/i5W3pz7 GitHub: https://ift.tt/cLsNU6K
10 by HenryNdubuaku | 1 comments on Hacker News.
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention is the right primitive for this, and FFN parameters are wasted at this scale. Simple Attention Networks: the entire model is just attention and gating, no MLPs anywhere. Needle is an experimental run for single-shot function calling for consumer devices (phones, watches, glasses...). Training: - Pretrained on 200B tokens across 16 TPU v6e (27 hours) - Post-trained on 2B tokens of synthesized function-calling data (45 minutes) - Dataset synthesized via Gemini with 15 tool categories (timers, messaging, navigation, smart home, etc.) You can test it right now and finetune on your Mac/PC: https://ift.tt/cLsNU6K The full writeup on the architecture is here: https://ift.tt/J81foIv... We found that the "no FFN" finding generalizes beyond function calling to any task where the model has access to external structured knowledge (RAG, tool use, retrieval-augmented generation). The model doesn't need to memorize facts in FFN weights if the facts are provided in the input. Experimental results to published. While it beats FunctionGemma-270M, Qwen-0.6B, Granite-350M, LFM2.5-350M on single-shot function calling, those models have more scope/capacity and excel in conversational settings. We encourage you to test on your own tools via the playground and finetune accordingly. This is part of our broader work on Cactus ( https://ift.tt/Lsay4TY ), an inference engine built from scratch for mobile, wearables and custom hardware. We wrote about Cactus here previously: https://ift.tt/M2upWRs Everything is MIT licensed. Weights: https://ift.tt/i5W3pz7 GitHub: https://ift.tt/cLsNU6K
Monday, May 11, 2026
Sunday, May 10, 2026
New top story on Hacker News: Ask HN: What Are You Working On? (May 2026)
Ask HN: What Are You Working On? (May 2026)
15 by david927 | 34 comments on Hacker News.
What are you working on? Any new ideas that you're thinking about?
15 by david927 | 34 comments on Hacker News.
What are you working on? Any new ideas that you're thinking about?
Saturday, May 9, 2026
Friday, May 8, 2026
New top story on Hacker News: Show HN: GETadb.com – every GET request creates a DB
Show HN: GETadb.com – every GET request creates a DB
10 by nezaj | 1 comments on Hacker News.
Hey HN! We made GETadb.com, so it's easier to get agents to build you full stack apps. You don't need to give them any credentials. Just by loading a GET request, they get access to a database, a sync engine, and abstractions for auth, presence, and streams. To see what the agent sees, you can load https://getadb.com/new There's two fun things about how it's implemented: 1. If you curl the home page, it the agent content rather than human content. We do this by detecting the 'Sec-Fetch-Mode' header. It's not perfect, but gets the job done for Claude Code et al. 2. For an agent to spin up an app, they make _two_ fethes. (1) getadb.com/guide tells them to generate a uuid, and fetch (2) getadb.com/provision/. We did this, because just about half of the popular web-based app builders cache URLs globally, even if you return no-store headers. To get around this we just instruct the agent to generate unique URLs You may wonder: Why GET requests, rather than POST requests? It's because then you can build in surprising places. For example, we get meta.ai to build an app inside the artifact preview: https://ift.tt/ryzGvMh Under the hood, this is possible because the whole infra is mult-tenant from ground up. We already announced how that works on HN, but if you're curious here's the essay for it: https://ift.tt/RtCs5F6
10 by nezaj | 1 comments on Hacker News.
Hey HN! We made GETadb.com, so it's easier to get agents to build you full stack apps. You don't need to give them any credentials. Just by loading a GET request, they get access to a database, a sync engine, and abstractions for auth, presence, and streams. To see what the agent sees, you can load https://getadb.com/new There's two fun things about how it's implemented: 1. If you curl the home page, it the agent content rather than human content. We do this by detecting the 'Sec-Fetch-Mode' header. It's not perfect, but gets the job done for Claude Code et al. 2. For an agent to spin up an app, they make _two_ fethes. (1) getadb.com/guide tells them to generate a uuid, and fetch (2) getadb.com/provision/
Thursday, May 7, 2026
Wednesday, May 6, 2026
Tuesday, May 5, 2026
Monday, May 4, 2026
Sunday, May 3, 2026
Saturday, May 2, 2026
Friday, May 1, 2026
Thursday, April 30, 2026
Wednesday, April 29, 2026
Tuesday, April 28, 2026
Monday, April 27, 2026
New top story on Hacker News: China blocks Meta's acquisition of AI startup Manus
China blocks Meta's acquisition of AI startup Manus
7 by yakkomajuri | 0 comments on Hacker News.
https://ift.tt/ZNjfKSk...
7 by yakkomajuri | 0 comments on Hacker News.
https://ift.tt/ZNjfKSk...
Sunday, April 26, 2026
Saturday, April 25, 2026
Subscribe to:
Posts (Atom)