maxrumpf

such a (visually) beautiful blogpost.

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)

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

> "compatible" instead of "comparable."

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

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

are you a maintainer on npm?

congratulations!

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.

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

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.

I imagine color consistency will be such a pain here.

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.

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.