HackerTrans
トップ新着トレンドコメント過去質問紹介求人

volatilityfund

no profile record

投稿

My research has build errors now and honestly should have always worked this way

github.com
3 ポイント·投稿者 volatilityfund·3 か月前·0 コメント

Walked dog, did groceries, folded laundry. Claude Code shipped. Thanks Farmer

github.com
5 ポイント·投稿者 volatilityfund·3 か月前·0 コメント

The tool that won't let AI say anything it can't cite

github.com
36 ポイント·投稿者 volatilityfund·3 か月前·15 コメント

Claude Code plugin for LLM research with typed claims and conflict detection

github.com
3 ポイント·投稿者 volatilityfund·3 か月前·0 コメント

I use Pollinations as a lightweight LLM back end (faster than Hugging Face)

pollinations.ai
2 ポイント·投稿者 volatilityfund·3 か月前·0 コメント

LLMs can't justify their answers–this CLI forces them to

wheat.grainulation.com
11 ポイント·投稿者 volatilityfund·3 か月前·19 コメント

A CLI that forces LLMs to defend their answers

deepwiki.com
4 ポイント·投稿者 volatilityfund·3 か月前·0 コメント

Missing layer between LLMs and engineering decisions: evidence-graded reasoning

github.com
1 ポイント·投稿者 volatilityfund·3 か月前·0 コメント

[untitled]

1 ポイント·投稿者 volatilityfund·4 か月前·0 コメント

コメント

volatilityfund
·3 か月前·議論
My data is from Anthropic

Not sure how it works under the hood, probably a better question for them

Perhaps you are misunderstanding the entire premise of this project, this is not an LLM
volatilityfund
·3 か月前·議論
The ecosystem is 8 tools plus a claude code plugin, the unlock was composing those tools (I don't regularly use all 9). The 5x claim was from /insights (claude code)

Not for everyone, but it radically changed how I build. Senior engineer, 10+ years

Now it's trivial to run multiple projects in parallel across claude sessions (this was not really manageable before using wheat)

Genuinely don't remember the last time I opened a file locally
volatilityfund
·3 か月前·議論
5x productivity boost in merged PRs (lots of open PR & merge rate goes down, but net positive)

Starting to build custom tooling around new "friction" points in dev cycle

(eng IC perspective)