HackerTrans
TopNewTrendsCommentsPastAskShowJobs

rapiz

no profile record

Submissions

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

github.com
10 points·by rapiz·bulan lalu·4 comments

Show Me Less Output

blog.yqiao.me
1 points·by rapiz·2 bulan yang lalu·0 comments

AI-Declaration.md

github.com
2 points·by rapiz·2 bulan yang lalu·0 comments

Anthropic banned Pi, a third party harness

3 points·by rapiz·3 bulan yang lalu·6 comments

comments

rapiz
·bulan lalu·discuss
IMHO it's better than those vibing thousands of lines and claim it's something ground breaking and production grade.
rapiz
·bulan lalu·discuss
Dang I made the same thing the same day https://news.ycombinator.com/item?id=48374308
rapiz
·2 bulan yang lalu·discuss
fyi https://github.com/multica-ai/multica
rapiz
·2 bulan yang lalu·discuss
US seems to be learning from China very quick. Congrats.
rapiz
·3 bulan yang lalu·discuss
The graphics looks nice. What's the difference from other AI towns thought?
rapiz
·3 bulan yang lalu·discuss
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 bulan yang lalu·discuss
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 bulan yang lalu·discuss
Just for fun. I asked Claude to build an online rater using the rubrics https://yujqiao.github.io/bs-index/
rapiz
·3 tahun yang lalu·discuss
We're talking about a product and you present a story.