Reader

Latest posts from blogs I follow

3000 entries
60 pages

llm 0.37.2(opens in new tab)

Release: llm 0.37.2 Fixes a security issue reported by Daniel de Araujo in GHSA-v9h7-jj4g-f862 and GHSA-r639-rr7r-x72w. LLM has a mechanism called extra-openai-models.yaml - now managed by the new-in-0.37 llm openai endpoint add command - for using LLM with OpenAI-compatible API ...

Anthropic's IPO roadshow video(opens in new tab)

Anthropic's IPO roadshow video Anthropic kicked off their IPO roadshow yesterday, and their roadshow video has some previously unreleased information about how their business works. The section on "Approach to compute" with co-founder Tom Brown is particularly interesting, describing how ...

(opens in new tab)

The goal of the e18e.dev collective is to make the JavaScript ecosystem less JavaScript (i.e. bad). Looks like they’re ready to tackle the ender dragon because they launched a new framework performance project. Looking at the core web vitals it’s ...

The Villa of Ormen(opens in new tab)

As a child, I was never a fan of any actor or singer. David Bowie is the closest thing to a “music idol” I’ve ever had. I never had a poster of him on my wall, or a T-shirt with ...

The Bitter Wall(opens in new tab)

A chart of output quality against model intelligence: a purple curve rises steeply, then flattens under a brick wall labeled The Bitter Wall, whose height is marked What you can articulate; a teal arrow labeled Better articulation: harness + context ...

llm-gemini 0.36(opens in new tab)

Release: llm-gemini 0.36 Gemini 4 Carbon was announced two weeks ago for "a subset of cyber defenders", but today it's available to everyone else. This is Google's best ever Gemini, priced at $2/million input and $10/million output at launch (that's ...

#504: Who turned the GIL back on?(opens in new tab)

Topics covered in this episode: PyPI's redesigned project pages now warn when provenance changes gilguard catches the import that turns the GIL back on pip 26.3: pylock extras, and pip says plainly that untrusted wheels aren't safe All developer tools ...

Making a Website in 2026(opens in new tab)

Pete Millspaugh has a great post over on the Val Town blog where he documents his attempt at making generating the same website across a variety of AI tools. I love the post. Here are a couple of thoughts that ...

(opens in new tab)

I’m still reading Japanese detective fiction! These books like to reference each other. I think the authors have some kind of honkaku metaverse going on. Since my last note I finished Death Among the Undead (2017) and also read: The ...

Yonkers Rises(opens in new tab)

Tool: Yonkers Rises I realized I didn't know where Yonkers was, so I looked it up on Google Maps and then, to help embed its location and shape in my head (and to try out Claude Fable 5.2's 3D modeling ...

llm-anthropic 0.31(opens in new tab)

Release: llm-anthropic 0.31 Anthropic released Fable 5.2 and Mythos 5.2 today. Fable 5.2 is currently ranked first on Artificial Analysis. Anthropic say it "solved two open problems in the physics of black holes", so clearly their internal benchmarks have become ...