Hacker News Reader

maxrumpfon Training a 4B model to produce 81% faster query plans than Postgres

such a (visually) beautiful blogpost.

maxrumpfon RAG Is Simpler Than You Think

The easiest way to strip complexity is to expose simple tools to an agent model like SID-1 that can use them well. It makes more of an effort for hard questions, and little effort for easy ones.

(found of sid.ai so obv biased)

maxrumpfon Beating GPT-5.6 Sol on retrieval with 100x cheaper open models

SID-1 co-author here: was a lot of fun writing it. want to chat? just firstname at domain.

maxrumpfon Qwen 3.8

> "compatible" instead of "comparable."

It boggles my mind how you can train a frontier model but not write a tweet without an obvious typo.

maxrumpfon Show HN: HelixDB – A Graph Database built on Object-storage

does it support fts/vector on edges of the graph?

maxrumpfon Please don't spam people looking for employment. It's just cruel

are you a maintainer on npm?

maxrumpfon Launch HN: Voker (YC S24) – Analytics for AI Agents

congratulations!

maxrumpfon Chroma Context-1: Training a Self-Editing Search Agent

We think this is a pretty sad day for research: Some context about Chroma's model. https://x.com/maxrumpf/status/2037365748973384154?s=20

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

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.

maxrumpfon New anti-speeding system coming to Australia is dangerous

This comment section is scary. Hacker news advocating FOR nanny technology?!

maxrumpfon N=1 software and the unreasonable effectiveness of Excel

Excel is awful in almost every way, but I just wish more software was as customizable.

I can get (even more) customization by using pandas etc., but it's usually much slower and you get much less of an intuition about the data.

maxrumpfon Polychromatic Pixels

I imagine color consistency will be such a pain here.

maxrumpfon Tell HN: Ever think of applying to YC? Do it this weekend for S24

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.

maxrumpfon Mixture-of-Depths: Dynamically allocating compute in transformers

The abstract and the rest of the paper don't really match imo. It's not really allocating more to some sequences, but just introducing ~dropout. Might be different sides to the same coin, but was still a weird read.