brimtown
Joined 13 years ago
Karma
133
Submissions
66
Member since
Mar 26
Recent submissions
Comment · 2 months ago
Comment · 4 months ago
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.
Comment · 9 months ago
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 :)
Comment · 9 months ago
“standardize the intersection, expose the union” is a great phrase I hadn’t heard articulated before
Comment · 9 months ago
I’m currently letting Claude build and play its own Dwarf Fortress clone, as an installable plugin in Claude Code
Comment · 9 months ago
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
Comment · 10 months ago
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/
Comment · 1 year ago
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://www.anthropic.com/research/natural-language-autoenco...