Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Snuggly73
2 days ago
|
parent
|
context
|
favorite
| on:
Generative AI coding tools and agents do not work ...
New benchmark for competitive coding dropped yesterday -
https://livecodebenchpro.com/
Apparently models are not doing great for problems out of distribution.
p1dda
2 days ago
[–]
It goes to show that the LLMs aren't intelligent in the way humans are. LLMs are a really great replacement for googling though
reply
Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Apparently models are not doing great for problems out of distribution.