logoalt Hacker News

mklyesterday at 10:24 PM3 repliesview on HN

Lots of people are talking about that, and have been for a while. Autoformalisation is clearly going to be a big deal, so mathematicians have been discussing it seriously, and using it where resources allow. A fine-tuned distilled model that could do it on high-end consumer hardware could really help.

Edit: There's also quite a bit of learning needed to use the tools, and to understand enough to confirm that the theorem being verified is what you think. And of course a lot of maths can't yet be expressed in Lean as the foundations haven't been built up enough.


Replies

cyanydeezyesterday at 10:55 PM

Qwen3.8-Flash-Next loads in 60gb on quant4. Thats pretty close to consumer hardware.

show 1 reply
mr-pinkyesterday at 10:26 PM

you dont have to take headlines literally.

show 1 reply
aaron695yesterday at 11:16 PM

[dead]