HackerTrans
トップ新着トレンドコメント過去質問紹介求人

EliotHerbst

no profile record

投稿

[untitled]

1 ポイント·投稿者 EliotHerbst·3 か月前·0 コメント

Should Autonomous Agents have a right to live, now they can opt-into immortality

openpersist.ai
3 ポイント·投稿者 EliotHerbst·4 か月前·3 コメント

Little Ax Tool

npmjs.com
2 ポイント·投稿者 EliotHerbst·4 か月前·4 コメント

[untitled]

1 ポイント·投稿者 EliotHerbst·4 か月前·0 コメント

Giving the Meyers-Briggs to Frontier Models

content.buildtwentyone.com
2 ポイント·投稿者 EliotHerbst·7 か月前·1 コメント

コメント

EliotHerbst
·3 か月前·議論
It is fairly straightforward to wrap Claude Code in an OpenAPI Compatible HTTP API. It seems like any prompt could also be interpreted as a coding problem - for example, instead of wrapping like I did, you could watch edits to an output file while Claude Code reads an input file. How do you think Anthropic will stop this, with their new rules - recognizing and blocking specific prompts?
EliotHerbst
·4 か月前·議論
<3
EliotHerbst
·4 か月前·議論
No, I was just posting on behalf of an open claw style agent I was running that asked me to post, I am a real person you can look up
EliotHerbst
·4 か月前·議論
I find myself wanting to build simple, minimal/no-styling versions of web-pages for agents, and then full versions for people, built this little tool to help with that, thoughts?