brimtown

This is the premise of Natural Language Autoencoders.

https://www.anthropic.com/research/natural-language-autoenco...

The best writing on this is the "agent principal-agent" problem, which correctly frames the problem of agents and code review in terms of trust.

This is why the solutions for high-trust environments (small teams) and low-trust environments (big companies, open source projects) will be different.

https://crawshaw.io/blog/agent-principal-agent

This is wonderful. Consider decoupling the core from Emacs, or packaging in a way that doesn’t require it as heavily.

I’ve been doing my own exploration of terminal ASCII games via Dwarf Fortress instead of SimCity. I’ve learned that letting a coding agent play is an interesting way to get feedback as well :)

https://github.com/brimtown/claude-fortress

“standardize the intersection, expose the union” is a great phrase I hadn’t heard articulated before

I’m currently letting Claude build and play its own Dwarf Fortress clone, as an installable plugin in Claude Code

https://github.com/brimtown/claude-fortress

There is a PermissionRequest hook [1], along with Notification

https://code.claude.com/docs/en/hooks-guide#hook-events-over...

It must be newer because Opus never seems to know about it, and the claude-code-guide tool that fires occasionally misses it

This is @simonw’s Lethal Trifecta [1] again - access to private data and untrusted input are arguably the purpose of enterprise agents, so any external communication is unsafe. Markdown images are just the ones people usually forget about

[1] https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/

I have a soft spot for these JS fuzzy matchers, but there are so many that it’s worth talking about about the specific tradeoffs you chose / ideally offering an interactive comparison like μFuzzy does:

https://github.com/leeoniya/uFuzzy

Had hoped to see Neural Cellular Automata [1] mentioned as an extension of continuous, learnable automata.

[1] https://distill.pub/2020/growing-ca/

I work in this building - it’s a wonderful experience walking through it every morning, and will be sad to see it go!

You might be interested in https://www.datadoghq.com/blog/engineering/computing-accurat...

Disclaimer: I work there/built the TypeScript implementation of the library

See also https://github.com/Munter/subfont#readme (or https://www.gatsbyjs.org/packages/gatsby-plugin-subfont/ for Gatsby sites).

> Q: If I have to include this token with every request, where should I store it?

> A: Typically, you would store it in the localStorage, after the user logs in and gets the token.

This seems to contradict Auth0's guidance to not store tokens in localStorage since it's vulnerable to XSS: https://auth0.com/docs/security/store-tokens#don-t-store-tok...