HackerTrans
TopNewTrendsCommentsPastAskShowJobs

maxrumpf

no profile record

Submissions

Training SID-1 to beat GPT-5 at search with 1k+ QPS RL

turbopuffer.com
12 points·by maxrumpf·2 mesi fa·0 comments

Scaling compute for retrieval by 5 OOMs: SID-1 tech report

sid.ai
4 points·by maxrumpf·7 mesi fa·1 comments

comments

maxrumpf
·mese scorso·discuss
does it support fts/vector on edges of the graph?
maxrumpf
·mese scorso·discuss
are you a maintainer on npm?
maxrumpf
·2 mesi fa·discuss
congratulations!
maxrumpf
·4 mesi fa·discuss
We think this is a pretty sad day for research: Some context about Chroma's model. https://x.com/maxrumpf/status/2037365748973384154?s=20
maxrumpf
·7 mesi fa·discuss
This is the tech report for a model I helped work on. I'm biased, but it turned out very well.

We essentially let the model learn to retrieve like a human would: Make a first search, read the results, and then make another. This lets the model be vastly better than pre-programmed pipelines. We test this extensively and compare against implementing this with API models (like Sonnet 4.5 and GPT-5.1). SID-1 compares favorably.

Happy to answer any questions or get feedback. First and foremost: Enjoy the read. It's much more detailed than most tech reports.
maxrumpf
·2 anni fa·discuss
The weirdest thing people do is make up criteria that YC supposedly uses to reject people. There was such a huge diversity in our batch: From 20 y/o to 40+. Foreign, domestic. Credentialed, not credentialed. $1M rev run rate, $0 run rate. Just apply.