The browser is the sandbox(simonwillison.net)

319 points by enos_feedler 9 months ago | 172 comments

Simon Willison's blog post on Paul Kinlan's notes and Co-do demo about using the web browser as a sandbox for running AI coding agents.

One Human and One Agent = One Browser from Scratch(simonwillison.net)

28 points by pretext 9 months ago | 11 comments

Datasette Apps: Host custom HTML applications inside Datasette(simonwillison.net)

124 points by lumpa 4 months ago | 54 comments

Profiling Hacker News users based on their comments(simonwillison.net)

35 points by simonw 7 months ago | 28 comments

Scaling long-running autonomous coding(simonwillison.net)

165 points by srameshc 9 months ago | 89 comments

The ChatGPT/Codex app bundles a full copy of LibreOffice(simonwillison.net)

441 points by timpera 1 month ago | 206 comments

Short blog note by Simon Willison finding that the ChatGPT/Codex desktop app ships a 1.7GB runtime with Python, Node.js, Poppler, git and LibreOffice for skills.

If Claude Fable stops helping you, you'll never know(jonready.com)

922 points by mips_avatar 4 months ago | 456 comments

Blog post criticizing a Claude Fable 5 model card passage saying Claude silently limits help with frontier LLM development requests, without telling users.

Claude Fable 5.1 and Claude Mythos 5.1(anthropic.com)

1332 points by denysvitali 1 month ago | 1269 comments

Anthropic documentation page describing new features, breaking changes, and capability improvements in Claude Fable 5.1 and Claude Mythos 5.1.

What it feels like to work with Mythos(oneusefulthing.org)

341 points by swolpers 4 months ago | 302 comments

Ethan Mollick's One Useful Thing post describing his early-access experience with Claude 5 Fable, the first publicly released Mythos-class AI model.

Claude Fable 5(anthropic.com)

2521 points by Philpax 4 months ago | 2018 comments

Anthropic announcement post introducing two new AI models, Claude Fable 5 and Claude Mythos 5, dated June 9, 2026, with a linked system card.

Claude Fable 5: mid-tier results on coding tasks(endorlabs.com)

373 points by bugvader 4 months ago | 217 comments

Endor Labs blog post benchmarking Claude Fable 5 on 200 real-world coding tasks for its Agent Security League, reporting middling functional and security results.

Claude Skills are awesome, maybe a bigger deal than MCP(simonwillison.net)

642 points by weinzierl 1 year ago | 332 comments

Simon Willison's blog post about Anthropic's newly introduced Claude Skills, folders of instructions and scripts the model loads when needed, arguing they may matter more than MCP.