[interleave]

Amazing! I've been in a similar autoresearch-y rabbit-hole lately with getting Apple's 3B Foundation Model to match Sonnet 4.6 on a very specific task.

The result was: 90% parity achieved with a weird combination of a fine-tuned adapter + 1 deterministic step.

I wrote the whole thing down here: https://alexisrondeau.me/tada/research/FMDiscovery/dashboard... which includes the question, the answer, the 96 experiments and their lineage etc. etc.

[docheinestages]

> I wrote the whole thing down here

I like the idea, but it looks really hard to read. Try reading it top to bottom without skipping.

[interleave]

Oh, thank you for noticing.

Is it a layout issue for you (it lays out better on desktop) or the language of the text or...? Let me know!

[docheinestages]

The main issue is the amount of information I have to go through to understand what I'm looking at. It's one of the side effects of writing with AI. Because it sees all tokens at once, it doesn't realize a reader might have no clue at all. What I recommend is trying to reduce the entire thing in 1-2 paragraphs that you wrote yourself. Cleaning up unnecessary prose and tucking away data that not everyone might be immediately interested in.