HackerLangs
TopNewTrendsCommentsPastAskShowJobs

pstorm

135 karmajoined 4 tahun yang lalu

comments

pstorm
·kemarin·discuss
Cost and intelligence aren't the only axes. Terra has better latency and output speed than Sol for example.
pstorm
·bulan lalu·discuss
I’ve been building this out too, and your comment made me realize the missing piece for me. I’ve given the agents tools to validate its own work, but I haven’t improved the experience of humans verifying the agents’ work.
pstorm
·2 bulan yang lalu·discuss
I played again and found issues. After level 40ish, basically nothing can hurt you. You heal too fast. And once I got past level 80ish, I was running so fast, I ran through walls. And the saddest part, I got to level 200+ and couldn’t die to lock in my high score! It was a fun time though, thanks for sharing this game!
pstorm
·2 bulan yang lalu·discuss
This was more fun than I was expecting. Nice way to waste 20 min!
pstorm
·2 bulan yang lalu·discuss
At a minimum, you increase top-k to cast a wider net, then after reranking, take the N you really want. You have to play around with it a bit, but that’s the idea.
pstorm
·2 bulan yang lalu·discuss
I’m very surprised this isn’t getting more attention. Am I missing something?

It seems at or above SOTA on the given benchmarks, doesn’t have context rot, is orders of magnitude faster, and uses less compute that current transformer models. I suppose it’s just an announcement and we can’t test it ourselves yet.
pstorm
·2 bulan yang lalu·discuss
Just fyi, for RAG/similarity search, adding a reranker was much bigger pay off than switching embedding models.
pstorm
·6 bulan yang lalu·discuss
I built one of the top 3 results on Google when you search “compound interest calculator” and a dozen other similarly popular calculator pages.

The value isn’t the interface, it’s the trust that its calculations are accurate. I can’t tell you how many meetings I had with accountants and finance people to validate all the calculations.