Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
fellowniusmonk
27 days ago
|
parent
|
context
|
favorite
| on:
GPT-5.2
5.2 is performing worse in technical reading comprehension for information and logic dense puzzles. It's way more confidently wrong and stubborn about understanding definitions of words.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: