HackerTrans
トップ新着トレンドコメント過去質問紹介求人

rapiz

no profile record

投稿

Show HN: 100cc - Roll your own Claude in 100 lines

github.com
10 ポイント·投稿者 rapiz·先月·4 コメント

Show Me Less Output

blog.yqiao.me
1 ポイント·投稿者 rapiz·2 か月前·0 コメント

AI-Declaration.md

github.com
2 ポイント·投稿者 rapiz·2 か月前·0 コメント

Anthropic banned Pi, a third party harness

3 ポイント·投稿者 rapiz·3 か月前·6 コメント

コメント

rapiz
·先月·議論
IMHO it's better than those vibing thousands of lines and claim it's something ground breaking and production grade.
rapiz
·先月·議論
Dang I made the same thing the same day https://news.ycombinator.com/item?id=48374308
rapiz
·2 か月前·議論
fyi https://github.com/multica-ai/multica
rapiz
·2 か月前·議論
US seems to be learning from China very quick. Congrats.
rapiz
·3 か月前·議論
The graphics looks nice. What's the difference from other AI towns thought?
rapiz
·3 か月前·議論
Benchmark is not designed for the red team testing. I don't even think it make sense to "fix" the issue the article is suggesting. Yes, you can break the running contest by driving a car. Does this mean we need to make running contest car-proof?
rapiz
·3 か月前·議論
100% agree. it not only applies to the training time but also applies to the inference time. Domain specific context and skills will be the only moat for companies
rapiz
·3 か月前·議論
Just for fun. I asked Claude to build an online rater using the rubrics https://yujqiao.github.io/bs-index/
rapiz
·3 年前·議論
We're talking about a product and you present a story.