Topics /
The most popular blog posts about ai & machine learning on Hacker News. 3,091 posts.
It’s well-known at this point that GPT-4/GPT-3.5-turbo is non-deterministic, even at temperature=0.0. This is an odd behavior if you’re used to dense decoder-only models, where temp=0 should imply greedy sampling which should imply full determinism, because the logits for the next token should be a pure function of…
How I run CLIP (ViT-B-32) on iPhone to search the Photos album offline with Queryable: exporting Core ML text and image encoders for CLIP photo search
Trump admin sees China behind opposition to AI data centers
Identifying them as such only lets companies like OpenAI off the hook.
An extensive tutorial on how to implement a neural network in JavaScript with deeplearn.js to perform machine learning in JavaScript. You can bring neural networks to your browser by using the performance benefits of WebGL. Deeplearn.js makes it possible to implement a WebGL powered neural network ...
Hatching... Cursor Shenanigans Cursor, my beloved, started rate limiting shenanigans a few days back. For a good 2 weeks after June 16, 2025, we had almo...
Why agents need project documentation instead of retrieval from old conversations.
ChatGPT and LLMs amplify both insight and illusion. They are not knowledge engines, but confidence engines shaping how we think and learn.
The site for the Remako Mod, a Final Fantasy VII mod that uses AI to improve the graphics of this classic JRPG.
So the big news this week is that o3, OpenAI’s new language model, got 25% on FrontierMath. Let’s start by explaining what this means.
Are people using AI, or is the organization learning from it? What changed because we spent those tokens? And who moves discoveries from individuals to teams to organizational capabilities?
I fought against Google’s Pentagon AI deal from the inside. Powerful people and institutions failed to keep their AI ethics promises under pressure.
How to build a RAG system that's fully self-hosted.
Some of the latest Intel processors support the AVX-512 family of vector instructions. These instructions operate on blocks of 512 bits (or 64 bytes). The benefit of such wide instructions is that even without increasing the processor clock speed, systems can still process a lot more data. Most code today operators…
Certainly the industry is transforming, however, the people and organizations falling into the trap of no longer reading and writing code only do so at their peril.
A developer's guide to downloading and running LLMs on macOS, for experimentation and privacy.
Except for the SaaS, almost none of this is useful and I don't want to maintain any of it. I accidentally run a news outlet which is surely a liability. Sure, it has helped me "learn AI tooling" and I use many of these tools, but I didn't need them. I can't afford to maintain any of them, not in terms of time…
If we think writing code is dead, and AI is generating all codebases, I still think the bigger problem is people or full teams not knowing anything anymore about the system...
But for what I do use LLMs for, it’s invaluable.
I tried Claude Design yesterday and I have a theory for how this whole thing shakes out.
Last month I asked people to hack part of my YouTube video, specifically to de-pixelate the contents of a folder I had pixelated starting at the 4:57 mark. Your browser does not support the video tag. For years, people have used the censor tool to blur or pixelate out parts of videos where there's sensitive…
Data matters; infrastructure matters more
Tuesday was Stateless MCP day—the rollout of MCP 2.0, or the 2026-07-28 Model Context Protocol specification to use the more formal but less memorable name. This is the most significant …
If you’re on one of the cheaper Anthropic plans like me, it’s a pretty common scenario when you’re deep into Claude coding an idea, to hit a daily or weekly quota limit. If you want to keep going, you can connect to a local open source model instead of Anthropic. To monitor your current quota, type: /usage
<p>I've seen a few conversations where someone says something like this:</p> <blockquote> <p>I've been using an open-source LLM lately -- I'm a huge fan of not depending on OpenAI, Anthropic, or Google. But I'm really sad that the AI safety groups are trying to ban the kind of open-source LLM that I'm using.</p>…
One of my favourite uses for the GPT-3 AI language model is generating explanations of how code works. It’s shockingly effective at this: its training set clearly include a vast …
Writing code is cheap now - Agentic Engineering Patterns
