Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
bckr
27 days ago
|
parent
|
context
|
favorite
| on:
Learnings from building AI agents
Is there research solid knowledge on this?
baby
27 days ago
[–]
this trick is being used by many apps (including Github copilot reviews). The way I see it, is that if the agent has an eager-to-please problem, then you give it a way out
bckr
26 days ago
|
parent
[–]
Thanks. I was talking about the confidence measure.
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: