931
Embracing the parallel coding agent lifestyle
For a while now I’ve been hearing from engineers who run multiple coding agents at once—firing up several Claude Code or Codex CLI instances at the same time, sometimes in …
New
The latest blog posts to take off on Hacker News. 3,091 posts.
932
A History of Large Language Models
Large language models (LLMs) still feel a bit like magic to me. Of course, I understand the general machinery enough to know that they aren’t, but the gap between my outdated knowledge of the field and the state-of-the-art feels especially large right now. Things are moving fast. So six months ago, I decided to close…
933
Why do LLMs freak out over the seahorse emoji?
Investigating the seahorse emoji doom loop using logitlens.
934
What GPT-OSS leaks about OpenAI's training data
OpenAI recently released their open-weights model. Here we'll discuss how that inevitably leaks some information about their model training stack, and, on the way, show that GPT-5 was trained on phrases from adult websites....
935
NIST's DeepSeek "evaluation" is a hit piece
How NIST Turned Open Science into a Security Scare
936
937
938
Sora Update #1
We have been learning quickly from how people are using Sora and taking feedback from users, rightsholders, and other interested groups. We of course spent a lot of time discussing this before...
939
OpenAI Is Just Another Boring, Desperate AI Startup
What is OpenAI? I realize you might say "a foundation model lab" or "the company that runs ChatGPT," but that doesn't really give the full picture of everything it’s promised, or claimed, or leaked that it was or would be. No, really, if you believe its leaks to
940
Who needs Git when you have 1M context windows?
Lately I’ve heard a lot of stories of AI accidentally deleting entire codebases or wiping production databases . But in my case it was the other way around. I removed some working code and the LLM helped me to recover it.
941
What makes 5% of AI agents work in production?
Beyond the Prompt: Notes from the Context Frontier
942
How the AI Bubble Will Pop
The artificial intelligence boom is the most important economic story in the world. But the numbers just don't add up.
943
The RAG Obituary: Killed by agents, buried by context windows
I’ve been working in AI and search for a decade. First, I built Doctrine, the largest European legal search engine, and now I am building Fintool , an AI-powered financial research platform that helps institutional investors analyze companies, screen stocks, and make investment decisions.
944
Unix philosophy and filesystem access makes Claude Code amazing
Build the advantage your competitors can’t buy2025414 points216 commentsAI & Machine Learning details
If you've talked to me lately about AI, you've almost certainly been subject to a long soliloquy about the wonders of Claude Code. What started as a tool I ran in parallel with other tools to aid coding has turned into my full-fledged agentic operating system, supporting all kinds of workflows.
945
Designing agentic loops
Coding agents like Anthropic’s Claude Code and OpenAI’s Codex CLI represent a genuine step change in how useful LLMs can be for producing working code. These agents can now directly …
946
Comprehension debt: A ticking time bomb of LLM-generated code
Psst. If your boss won’t invest in training you in Specification By Example (BDD, ATDD), I’m running out-of-hours workshops on May 12 and 16 specifically for self-funding learners. £99 + UK VAT. An…
947
Companies are lying about AI layoffs?
Companies are saying that the economy and AI are causing the large amount of tech layoffs, but Vanessa Wingårdh looked at the H-1B visa data and noticed that the companies are lying. She argues that...
948
AI tools I wish existed
The models are powerful as is. But where are the tools?
949
ML on Apple ][+
Success! There is machine learning happening on my Apple ][+.
950
The AI coding trap
If you ever watch someone “coding”, you might see them spending far more time staring into space than typing on their keyboard.
951
The (economic) AI apocalypse is nigh
Like you, I'm sick to the back teeth of talking about AI. Like you, I keep getting dragged into discussions of AI. Unlike you‡, I spent the summer writing a book about why I'm sick of writing about AI⹋, which Farrar, Straus and Giroux will publish in 2026.
952
Why We Think
Special thanks to John Schulman for a lot of super valuable feedback and direct edits on this post. Test time compute (Graves et al. 2016, Ling, et al. 2017, Cobbe et al. 2021) and Chain-of-thought (CoT) (Wei et al. 2022, Nye et al. 2021), have led to significant improvements in model performance, while raising many…
953
Why today's humanoids won't learn dexterity
In this post I explain why today’s humanoid robots will not learn how to be dexterous despite the hundreds of millions, or perhaps many billions of dollars, being donated by VCs and major tech companies to pay for their training.
954
Can a model trained on satellite data really find brambles on the ground?
Can a model trained on satellite data really find brambles on the ground? We put a new model to the test with a field trip around Cambridge. The results...
955
Dario Amodei
How AI Could Transform the World for the Better
956
957
Pairing with Claude Code to rebuild my startup's website
Adventures using AI agents, especially Claude Code, and MCP Servers
958
Hacking with AI SASTs: An overview of ‘AI Security Engineers’ / ‘LLM Security Scanners’ for Penetration Testers and Security Teams
Reviewing AI Security Engineers: How ZeroPath found 200+ bugs in curl and why AI SASTs are becoming a viable replacement for traditional tools.
959
What happens when coding agents stop feeling like dialup?
From magical to frustrating in months. Why AI coding agents feel like dial-up internet and what ultra-fast inference could unlock for developer productivity.
960
AI was supposed to help juniors shine. Why does it mostly make seniors stronger?
AI was supposed to empower junior developers. In reality, it has become a tool that makes seniors more valuable while exposing the gaps in software culture.