Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Workaccount2
5 months ago
|
parent
|
context
|
favorite
| on:
OpenAI claims gold-medal performance at IMO 2025
I would fully expect every IMO participant grinds IMO problems for months before the competition.
I don't know why people hold training a model on like material as a negation of it's ability.
meroes
5 months ago
[–]
It shows models need RL for any new domain/level of expertise, which is contrary to what the marketers claim about LLMs and potential for AGI.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
I don't know why people hold training a model on like material as a negation of it's ability.