Y
Hacker News
new
|
ask
|
show
|
jobs
by
mangolie
202 days ago
https://x.com/deepseek_ai/status/1995452646459858977
Boom
3 comments
andy12_
202 days ago
Do note that that is a different model. The one we are talking about here, DeepSeekMath-V2, is indeed overcooked with math RL. It's so eager to solve math problems, that it even comes up with random ones if you prompt it with "Hello".
https://x.com/AlpinDale/status/1994324943559852326?s=20
link
yorwba
202 days ago
That's a different model:
https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale
link
simianwords
202 days ago
Oh you may be correct. Are these models general purpose or fine tuned for mathematics?
link
https://x.com/AlpinDale/status/1994324943559852326?s=20