HackerTrans
トップ新着トレンドコメント過去質問紹介求人

secbear

no profile record

投稿

Show HN: Neuron – Independent Rust crates for building AI agents

secbear.github.io
1 ポイント·投稿者 secbear·5 か月前·0 コメント

Show HN: Nix-sandbox-MCP: Reproducible, isolated code execution for Claude/LLMs

github.com
2 ポイント·投稿者 secbear·5 か月前·1 コメント

コメント

secbear
·5 か月前·議論
Totally agree. I've found in many cases it's easier to roll your own software/patch existing software with AI than to open an issue, submit a PR, get it reviewed/merged, etc. Let alone buying software
secbear
·5 か月前·議論
seems pretty solid from a security perspective actually
secbear
·5 か月前·議論
[flagged]
secbear
·5 か月前·議論
Hard mode- constant auto-complete suggestions that are right ~50% of the time
secbear
·5 か月前·議論
The finding that self-generated skills provide negative benefit (-1.3pp) while curated skills give +16.2pp is the most interesting result here imo. Big discrepancy, but makes sense. Aligns with the thought that LLMs are better consumers of procedural knowledge than producers of it.

+4.5pp for software engineering is suspiciously low compared to +51.9pp for healthcare. I suspect this reflects that frontier models already have strong SWE priors from training data, so skills add less marginal value. If true, skills become most valuable precisely in the domains where models are weakest — which is where you'd actually want to deploy agents in production. That's encouraging.
secbear
·5 か月前·議論
I feel similar... OpenClaw has lots of vulnerabilities, and it's very messy, but it also brought self-hosted cron-based agentic workflows to your favorite messaging channel (iMessage, telegram, slack, WhatsApp, etc.), which shouldn't be overlooked
secbear
·5 か月前·議論
Nice, have you considered adding support for agents/commands as a part of these presets?
secbear
·5 か月前·議論
Agreed, my experience and code quality with claude code and agentic workflows has dramatically increased since investing in learning how to properly use these tools. Ralph Wiggum based approaches and HumanLayer's agents/commands (in their .claude/) have boosted my productivity the most. https://github.com/snwfdhmp/awesome-ralph https://github.com/humanlayer
secbear
·5 か月前·議論
Amazing to see claude's reasoning and process through reversing this
secbear
·5 か月前·議論
Built this because I wanted Claude Code to run untrusted snippets without touching my system, but Docker felt heavy. Uses jail.nix (bubblewrap) for isolation. Currently supports Python, Node, Bash with persistent REPL sessions. Would love feedback on the interface design.