Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
epcoa
10 months ago
|
parent
|
context
|
favorite
| on:
Coping with dumb LLMs using classic ML
> ChatGPT is marginally better and will sometimes tell you straight up that an algorithm can't be rewritten as you suggest
Unfortunately this very often it gets wrong, especially if it involves some multistep process.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Unfortunately this very often it gets wrong, especially if it involves some multistep process.