The Warp Agent is now available as a standalone CLI that you can use anywhere – Ghostty, iTerm 2, VS Code, built-in Windows and Mac Terminals – and provides a superior experience for developers who do heavy terminal workflows.
Learn how OpenAI is improving ChatGPT across low-resource programming languages, with new evaluations for software engineering, SQLite, and COBOL migration.
Abel Jansma is a scientist studying emergence, higher-order interactions, information theory, and complex systems across biology and artificial intelligence.
The Pine Time is a $27 smart watch that runs open source firmware. I’ve had one sitting in the back of a drawer for a...
Anthropic framed Mythos and Project Glasswing as proof that frontier AI vulnerability research now needs gated access. We tested the public, patched cases with GPT-5.4 and Claude Opus 4.6 and found that the key building blocks are already accessible outside Glasswing, while reliable operationalization remains the real…
Late interaction makes retrieval more precise but turns every document into many vectors. Asymmetric quantization keeps query vectors precise and stores…
Full stack developer, open sourceror, serial entrepreneur.
AI is now able to decompile games and software in a matter of days. That's scary... but kind of exciting.
Executives love AI while ICs stay skeptical. The divide comes down to non-determinism: who is evaluated on judgment versus deterministic execution.
Thriving in a world of agents
Our latest ANN release supports scales of 100+ billion vectors in a single search index, with 200ms p99 query latency at 1k QPS and 92% recall.
We trained a model to predict speech from ultrasound video of the tongue, no speaking required. It reads open text, generalizes across people, and reaches a 15.6% word error rate on open-vocabulary speech.
This isn’t a joke, and it’s becoming a big problem
What in the world is Explorative Modeling?
You may already be aware of John Baez’s “Crackpot Index” , which provides a simple tongue-in-cheek scoring system for assessing whether a research contribution to physics is likely “revolutionary.” The list contain such gems as “40 points for comparing yourself to Galileo, suggesting that a modern-day Inquisition is…
Six AI assistants pursued an impossible £350 train refund in a simulated world, escalating to government officials, legal clinics and bank chargebacks.
This was an unusually hard post to write, because it flies in the face of everything else going on.
...also don't tell lies. But I'm getting ahead of myself already. I keep running into people online who openly say that they use AI to do their writing for t
Thoughts on technology, life and everything else.
Quint - Executable specs for reliable systems
The backlash against data centers is difficult to understand if your salary depends on your not understanding it.
Cursor has officially been acquired by SpaceX.
For those of you who don’t know, when I’m not writing novels, I spend my days as a software engineer, writing code. The software industry these days relies heavily on artificial intelligence. Because it has studied trillions of lines of publicly accessible source code, because code solves problems with testable right…
I asked Claude to look up the X-Plane 12 API and try to fly a Cessna from Hainan to somewhere nearby. It kept a pilot's log. Everything below is Claude's own notes from during the flight. I occasionally had to remind it to keep the pilot log running, and had to tell it when it crashed as xplane would quickly restart…
OpenAI shares a framework for tracking, investigating, and disclosing model misalignment, alongside six reports of unexpected or concerning model behavior.
Let's suppose I wanted to answer a question: is the tool X useful for the task Y. If I were scientific about this, I would analyze the properties of tool X and develop a model, and the task Y and the requirements for it and develop a model, and I would us...
Transformer language models are an emerging technology that is gaining increasingly broad real-world use, for example in systems like GPT-3 , LaMDA , Codex , Meena , Gopher , and similar models. However, as these models scale, their open-endedness and high capacity creates an increasing scope for unexpected and…
Yes, for a supported subset of SQL. To establish a baseline, I integrated the SQLLogicTest suite.
I’m tired of this phrase and this simple way of thinking about tools. This blog post is a wandering train of thought on the topic of what tools are and why it matters to be even slightly more mature in how we think about them.
MirrorCode is Epoch AI's benchmark for long-horizon coding: AI can reimplement entire programs end-to-end, with no access to the original source code.
