Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mikert89
28 days ago
|
parent
|
context
|
favorite
| on:
OpenAI claims gold-medal performance at IMO 2025
dude we have computers reasoning in english to solve math problems, what are you even talking about
simion314
28 days ago
[–]
I tested all available models on a harder highschool limit and they failed even with thinking mode, so I doubt OpenAI is telling the truth.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
