Entries
Filters: Sorted by date
Tracking the history of the now-deceased OpenAI Microsoft AGI clause
For many years, Microsoft and OpenAI’s relationship has included a weird clause saying that, should AGI be achieved, Microsoft’s commercial IP rights to OpenAI’s technology would be null and void. That clause appeared to end today. I decided to try and track its expression over time on openai.com.
[... 691 words]DeepSeek V4—almost on the frontier, a fraction of the price
Chinese AI lab DeepSeek’s last model release was V3.2 (and V3.2 Speciale) last December. They just dropped the first of their hotly anticipated V4 series in the shape of two preview models, DeepSeek-V4-Pro and DeepSeek-V4-Flash.
[... 703 words]Extract PDF text in your browser with LiteParse for the web
LlamaIndex have a most excellent open source project called LiteParse, which provides a Node.js CLI tool for extracting text from PDFs. I got a version of LiteParse working entirely in the browser, using most of the same libraries that LiteParse uses to run in Node.js.
[... 2,089 words]A pelican for GPT-5.5 via the semi-official Codex backdoor API
GPT-5.5 is out. It’s available in OpenAI Codex and is rolling out to paid ChatGPT subscribers. I’ve had some preview access and found it to be a fast, effective and highly capable model. As is usually the case these days, it’s hard to put into words what’s good about it—I ask it to build things and it builds exactly what I ask for!
[... 884 words]Is Claude Code going to cost $100/month? Probably not—it’s all very confusing
Anthropic today quietly (as in silently, no announcement anywhere at all) updated their claude.com/pricing page (but not their Choosing a Claude plan page, which shows up first for me on Google) to add this tiny but significant detail (arrow is mine, and it’s already reverted):
[... 1,202 words]Where’s the raccoon with the ham radio? (ChatGPT Images 2.0)
OpenAI released ChatGPT Images 2.0 today, their latest image generation model. On the livestream Sam Altman said that the leap from gpt-image-1 to gpt-image-2 was equivalent to jumping from GPT-3 to GPT-5. Here’s how I put it to the test.
[... 849 words]Changes in the system prompt between Claude Opus 4.6 and 4.7
Anthropic are the only major AI lab to publish the system prompts for their user-facing chat systems. Their system prompt archive now dates all the way back to Claude 3 in July 2024 and it’s always interesting to see how the system prompt evolves as they publish new models.
[... 1,024 words]Join us at PyCon US 2026 in Long Beach—we have new AI and security tracks this year
This year’s PyCon US is coming up next month from May 13th to May 19th, with the core conference talks from Friday 15th to Sunday 17th and tutorial and sprint days either side. It’s in Long Beach, California this year, the first time PyCon US has come to the West Coast since Portland, Oregon in 2017 and the first time in California since Santa Clara in 2013.
[... 606 words]Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7
For anyone who has been (inadvisably) taking my pelican riding a bicycle benchmark seriously as a robust way to test models, here are pelicans from this morning’s two big model releases—Qwen3.6-35B-A3B from Alibaba and Claude Opus 4.7 from Anthropic.
[... 602 words]Meta’s new model is Muse Spark, and meta.ai chat has some interesting tools
Meta announced Muse Spark today, their first model release since Llama 4 almost exactly a year ago. It’s hosted, not open weights, and the API is currently “a private API preview to select users”, but you can try it out today on meta.ai (Facebook or Instagram login required).
[... 2,607 words]Anthropic’s Project Glasswing—restricting Claude Mythos to security researchers—sounds necessary to me
Anthropic didn’t release their latest model, Claude Mythos (system card PDF), today. They have instead made it available to a very restricted set of preview partners under their newly announced Project Glasswing.
[... 1,296 words]The Axios supply chain attack used individually targeted social engineering
The Axios team have published a full postmortem on the supply chain attack which resulted in a malware dependency going out in a release the other day, and it involved a sophisticated social engineering campaign targeting one of their maintainers directly. Here’s Jason Saayman’a description of how that worked:
[... 357 words]Highlights from my conversation about agentic engineering on Lenny’s Podcast
I was a guest on Lenny Rachitsky’s podcast, in a new episode titled An AI state of the union: We’ve passed the inflection point, dark factories are coming, and automation timelines. It’s available on YouTube, Spotify, and Apple Podcasts. Here are my highlights from our conversation, with relevant links.
[... 3,558 words]Mr. Chatterbox is a (weak) Victorian-era ethically trained model you can run on your own computer
Trip Venturella released Mr. Chatterbox, a language model trained entirely on out-of-copyright text from the British Library. Here’s how he describes it in the model card:
[... 952 words]Vibe coding SwiftUI apps is a lot of fun
I have a new laptop—a 128GB M5 MacBook Pro, which early impressions show to be very capable for running good local LLMs. I got frustrated with Activity Monitor and decided to vibe code up some alternative tools for monitoring performance and I’m very happy with the results.
[... 1,195 words]Experimenting with Starlette 1.0 with Claude skills
Starlette 1.0 is out! This is a really big deal. I think Starlette may be the Python framework with the most usage compared to its relatively low brand recognition because Starlette is the foundation of FastAPI, which has attracted a huge amount of buzz that seems to have overshadowed Starlette itself.
[... 1,194 words]Profiling Hacker News users based on their comments
Here’s a mildly dystopian prompt I’ve been experimenting with recently: “Profile this user”, accompanied by a copy of their last 1,000 comments on Hacker News.
[... 976 words]Thoughts on OpenAI acquiring Astral and uv/ruff/ty
The big news this morning: Astral to join OpenAI (on the Astral blog) and OpenAI to acquire Astral (the OpenAI announcement). Astral are the company behind uv, ruff, and ty—three increasingly load-bearing open source projects in the Python ecosystem. I have thoughts!
[... 1,378 words]GPT-5.4 mini and GPT-5.4 nano, which can describe 76,000 photos for $52
OpenAI today: Introducing GPT‑5.4 mini and nano. These models join GPT-5.4 which was released two weeks ago.
[... 719 words]My fireside chat about agentic engineering at the Pragmatic Summit
I was a speaker last month at the Pragmatic Summit in San Francisco, where I participated in a fireside chat session about Agentic Engineering hosted by Eric Lui from Statsig.
[... 3,350 words]Perhaps not Boring Technology after all
A recurring concern I’ve seen regarding LLMs for programming is that they will push our technology choices towards the tools that are best represented in their training data, making it harder for new, better tools to break through the noise.
[... 391 words]Can coding agents relicense open source through a “clean room” implementation of code?
Over the past few months it’s become clear that coding agents are extraordinarily good at building a weird version of a “clean room” implementation of code.
[... 1,349 words]Something is afoot in the land of Qwen
I’m behind on writing about Qwen 3.5, a truly remarkable family of open weight models released by Alibaba’s Qwen team over the past few weeks. I’m hoping that the 3.5 family doesn’t turn out to be Qwen’s swan song, seeing as that team has had some very high profile departures in the past 24 hours.
[... 705 words]I vibe coded my dream macOS presentation app
I gave a talk this weekend at Social Science FOO Camp in Mountain View. The event was a classic unconference format where anyone could present a talk without needing to propose it in advance. I grabbed a slot for a talk I titled “The State of LLMs, February 2026 edition”, subtitle “It’s all changed since November!”. I vibe coded a custom macOS app for the presentation the night before.
[... 1,613 words]Writing about Agentic Engineering Patterns
I’ve started a new project to collect and document Agentic Engineering Patterns—coding practices and patterns to help get the best results out of this new era of coding agent development we find ourselves entering.
[... 554 words]Adding TILs, releases, museums, tools and research to my blog
I’ve been wanting to add indications of my various other online activities to my blog for a while now. I just turned on a new feature I’m calling “beats” (after story beats, naming this was hard!) which adds five new types of content to my site, all corresponding to activity elsewhere.
[... 614 words]Two new Showboat tools: Chartroom and datasette-showboat
I introduced Showboat a week ago—my CLI tool that helps coding agents create Markdown documents that demonstrate the code that they have created. I’ve been finding new ways to use it on a daily basis, and I’ve just released two new tools to help get the best out of the Showboat pattern. Chartroom is a CLI charting tool that works well with Showboat, and datasette-showboat lets Showboat’s new remote publishing feature incrementally push documents to a Datasette instance.
[... 1,756 words]Deep Blue
We coined a new term on the Oxide and Friends podcast last month (primary credit to Adam Leventhal) covering the sense of psychological ennui leading into existential dread that many software developers are feeling thanks to the encroachment of generative AI into their field of work.
[... 971 words]The evolution of OpenAI’s mission statement
As a USA 501(c)(3) the OpenAI non-profit has to file a tax return each year with the IRS. One of the required fields on that tax return is to “Briefly describe the organization’s mission or most significant activities”—this has actual legal weight to it as the IRS can use it to evaluate if the organization is sticking to its mission and deserves to maintain its non-profit tax-exempt status.
[... 680 words]Introducing Showboat and Rodney, so agents can demo what they’ve built
A key challenge working with coding agents is having them both test what they’ve built and demonstrate that software to you, their supervisor. This goes beyond automated tests—we need artifacts that show their progress and help us see exactly what the agent-produced software is able to do. I’ve just released two new tools aimed at this problem: Showboat and Rodney.
[... 2,023 words]