Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
brabel
25 days ago
|
parent
|
context
|
favorite
| on:
Agent design is still hard
If the LLM can test the code it will fix those issues automatically. That’s how it can keep going for hours and produce something useful. You need to review the code and tests obviously afterwards.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: