Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
fragmede
on Oct 5, 2024
|
parent
|
context
|
favorite
| on:
LLMs, Theory of Mind, and Cheryl's Birthday
"seems to" isn't good enough, especially since it's entirely possible to generate code that doesn't give the right answer. 4o is able to write some bad code, run it, recognize that it's bad, and then fix it, if you tell it to.
https://chatgpt.com/share/670086ed-67bc-8009-b96c-39e539791f...
Chinjut
on Oct 5, 2024
[–]
Did you actually run the "fixed" code here? Its output is an empty list, just like the pre-"fixed" code.
Chinjut
on Oct 5, 2024
|
parent
[–]
Hm, actually, it's confusing, because clicking the [>_] links where it mentions running code gives different code than it just mentioned.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
https://chatgpt.com/share/670086ed-67bc-8009-b96c-39e539791f...