Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
vessenes
10 months ago
|
parent
|
context
|
favorite
| on:
Ladder: Self-improving LLMs through recursive prob...
4.5 is not trained on code. And it shows. It is however to my eyes more fluid, thoughtful, has better theory of mind. It's like someone scaled up GPT-4, and I really like it.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
