Hacker News: brimtown

New comment by brimtown in "The primary purpose of code review is to find code that will be hard to maintain"

brimtown — Thu, 02 Jul 2026 14:09:12 +0000

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

The agent principal-agent problem

brimtown — Tue, 12 May 2026 16:24:46 +0000

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

Comments URL: https://news.ycombinator.com/item?id=48110462

Points: 1

# Comments: 0

We Will Not Be Divided

brimtown — Fri, 27 Feb 2026 01:12:24 +0000

Article URL: https://notdivided.org/

Comments URL: https://news.ycombinator.com/item?id=47174964

Points: 12

# Comments: 1

Pup – Datadog CLI

brimtown — Tue, 10 Feb 2026 03:08:11 +0000

Article URL: https://github.com/DataDog/pup

Comments URL: https://news.ycombinator.com/item?id=46954863

Points: 4

# Comments: 0

New comment by brimtown in "Show HN: Micropolis/SimCity Clone in Emacs Lisp"

brimtown — Thu, 05 Feb 2026 11:46:19 +0000

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

Synthetic Pretraining

brimtown — Mon, 02 Feb 2026 10:55:20 +0000

Article URL: https://vintagedata.org/blog/posts/synthetic-pretraining

Comments URL: https://news.ycombinator.com/item?id=46854590

Points: 3

# Comments: 0

New comment by brimtown in "What I learned building an opinionated and minimal coding agent"

brimtown — Sun, 01 Feb 2026 12:28:42 +0000

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

New comment by brimtown in "Letting Claude play text adventures"

brimtown — Wed, 21 Jan 2026 21:57:53 +0000

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

New comment by brimtown in "Show HN: Agent-of-empires: OpenCode and Claude Code session manager"

brimtown — Tue, 13 Jan 2026 12:23:17 +0000

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

New comment by brimtown in "Notion AI: Unpatched data exfiltration"

brimtown — Thu, 08 Jan 2026 00:51:22 +0000

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/

Train On Your Groupchat: LoRA and in-browser inference to fine-tune your friends

brimtown — Wed, 12 Nov 2025 19:20:34 +0000

Article URL: https://www.brimtown.com/train-on-your-groupchat

Comments URL: https://news.ycombinator.com/item?id=45904846

Points: 1

# Comments: 0

New comment by brimtown in "Show HN: Front End Fuzzy and Substring and Prefix Search"

brimtown — Fri, 31 Oct 2025 00:31:06 +0000

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