tools

Everyone is very concerned about being respectable, so I’m going to be the goofball who raises worst-case possibilities. I think there is a 1% chance we live in Minicrypt, and a 15% chance we function

Release: ttok 0.4 ttok is my CLI tool for counting tokens, using OpenAI's open source tiktoken library. It hasn't been in updated in a couple of years, but I finally fixed a Click warning, updated CI,

I've always been kind of into computers since I was young. And then when film started to move from analog film to digital, I became more interested in that aspect of it. And the visual effects workflo

I was a graph theory junkie long ago and even moved to Budapest for awhile to study among the greats. While I was there I started working on Barnette's Conjecture which came to occupy my thoughts over

Google’s new EmbeddingGemma 2 can run on a phone. The model travels light. The vectors need their own suitcase. At 10 million documents, full-size float32 vectors alone take 30.7 GB of RAM. We got ear

Since the Medicare breach, OpenAI has put in place additional monitoring to allow “immediate intervention” by staff to stop training if the company’s models access the internet in ways they’re not sup

I just sent the September edition of my sponsors-only monthly newsletter. If you are a sponsor (or start a sponsorship now) you can access it here. This month: More Fable class models A pricing war 3D

My comment on GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price — Hacker News.I'm a bit late with the pelicans because I was live-blogging the keynote: https://simonwillison.net/2026/Sep/2

I'm at OpenAI DevDay today, in Fort Mason, San Francisco. Same as last year I'll be live blogging the keynote and some other notes during the day. OpenAI gave me a free ticket and a seat in the 'creat

I tested Jev and five LLM judges across ten Arize Phoenix evaluators to measure how often their answers changed alongside accuracy, cost, and latency. The post What Jev’s probabilities reveal that rep

The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder. We can do amazing things with them, but unlocking their full potential requir

Radical Numerics, led by CEO Eric Nguyen, is deploying “biological chain‑of‑thought” and multimodal perception techniques to stay ahead of the evolving bio‑defense arms race, enabling rapid design of

Release: llm 0.36 New OpenAI models: gpt-6-sol for GPT-6 Sol and gpt-6-luna for GPT-6 Luna. #1702 Model plugins can now declare supports_conversation = False for models that only accept single-turn pr

Release: llm-typesafe 0.1a0 I built this new plugin for LLM to add support for TypeSafe AI's new Jev model. Install it like this: llm install llm-typesafe Then set an API key (get one here, the waitli

Being a computer scientist who refuses to find anything about LLMs interesting right now is a bit like being a geneticist who refuses to find anything interesting about the recently opened Jurassic Pa

TypeSafe’s Jev classifies, scores, and routes without generating text — up to hundreds of times cheaper than an LLM judge. What that changes for evals, confidence routing, and application architecture

Mem0 provides persistent user memory and agent memory; its vendor describes fact extraction, contradiction handling and relevant recall.

The contagion of fear Bryan Cantrill responds to the tweet by former Anthropic employee Jacob Coxon confirming that many Anthropic researchers believe AI 'could kill us all by the end of the decade'.

For a while, I must admit, it looked as if software developer roles like mine were done for. How could we fight against tireless robots? But our industry is slowly realizing that making truly cutting-

So you want to use OpenRouter? One of OpenRouter's selling points is that it 'handles fallbacks automatically and picks the most cost-effective option for each request', so you can call a single API e

Together Fine-Tuning adds the latest open-weight models, live experiment tracking, Expert LoRA, early stopping, tokenized dataset previews, pre-flight validation, and lower training prices on selected

Native is now the future of mobile at Shopify Shopify are moving from React Native back to separate Swift and Kotlin codebases for their native apps, for the exact reason you would expect: We decided

Creepy crawlies Konstantin Ryabitsev discusses how bad the 'background radiation' of abusive crawlers has become from the perspective of git.kernel.org, the official Git repository for the Linux kerne

**Title:** llm 0.35 **Summary:** Version 0.35 of the `llm` tool offers a command‑line interface for interacting with large language models. It allows users to issue prompts and retrieve model response

Tool: Mercator ↔ Equal Earth I got curious about the Equal Earth map projection that was recently voted on at the UN so I had GPT-6 Astra (medium) in ChatGPT Work build me this animated transition bet

The strongest argument I see for continuing to train much smarter models quickly is the need to build defensive systems against the dangers posed by other AI. [...] We will need powerful, aligned AI f

Introducing GPT-6 Astra for developers Blink and you'll miss it, but there's a familiar creature at 1m59s: Across the board, Astra has more attention to detail, better understanding of the user's prom

TIL: Using Blender with coding agents on macOS I've been having fun with Blender in ChatGPT Codex on my Mac recently. Getting it to work with coding agents is really easy: install the full Mac applica

GPT‑6 Astra is a lightweight, high‑performance OpenAI model that can be hired for under $6 an hour and outperforms rivals on tests such as FrontierMath (97.6%) and ARC‑AGI‑3 (99.9%). The authors burne

Release: llm 0.32.1 Fresh installs of LLM stopped working the other day because the OpenAI Python library dropped its usage of httpx, and it turned out LLM depended on that library but only installed

Simile AI’s CEO Joon Sung Park describes how the company moved from the 2024 “Summer of Simulative AI” and its landmark *Generative Agents* paper to building digital twins that predict individual and

My hypothesis is that there is a new opportunity for Extensible Software on the web. LLMs radically lower the cost of authoring extensions, and modern sandbox primitives lower the deployment cost and

Zep offers a knowledge graph for persistent user memory and shared organisational context through MCP, according to Zep.

Letta's agent-memory SDK supports persistent agent memory across managed cloud, self-hosted App Server or local deployment, according to Letta.

We Tracked a Shipment of Rare Books. It Ended at an Amazon AI Training Facility Excellent piece of reporting from 404 Media. For a while now there have been stories of book dealers receiving orders fo

I do agree that the public has a negative view of AI (and that this is a big problem), but I don’t think it is primarily caused by me or any other AI leader warning about AI’s risks. I think it is fun

Don't classify. Hallucinate! I still have quite a bit of older content on my blog that I never got round to tagging. My blog has 1,856 tags - likely too many to feed to an LLM in one go and say 'which

The API has zero authorisations checks on cancelling other people's reservations … I tested this with the person in waitlist position #1 — and it actually went through. So you've moved from #4 to #3 a

Gas Town was intended to be reusable, but I only ever wound up using it to build itself. Gas Town fell apart at the seams with Opus 4.7. Up through 4.6 it was working brilliantly. With 4.7 we saw the

Don't be a meat proxy Niklas Gruhn coins an excellent new term - meat proxy - for people who blindly copy and paste the output of AI systems to their peers. By all means, prompt AI. But don't just rel

Set up a nightly cron job that executes the prompt: fetch upstream changes to the <software> and rebase all local changes on top of upstream. Check that the software works as intended and replace the

at openai, many people hook their chatgpt up to slack. people really don't like when a coworker's chatgpt contacts them asking for help with a task, even when they'd be perfectly happy doing that same

AI Worming through Word Neat new prompt injection variant by Håkon Måløy, who found a way to upgrade prompt injection attacks against Microsoft Word to full self-replicating worms: An attacker places

The Together AI platform’s dedicated inference architecture consists of three immutable entities: **configs** (engine, GPU type/count, parallelism and optimization profile), **deployments** (a specifi

An Inside Look at the Relay Market Powering Token Resellers and Fraud Fascinating investigation by Matt Lenhard into the market that has grown up around reselling LLM tokens at a discount by pooling A

Poolside AI’s co‑CEO Eiso Kant explains that a small, top‑research team built a model‑factory capable of training Laguna S, a 118‑billion‑parameter mixture‑of‑experts model that outperforms the ~1 tri