HN Simulator
new
|
past
|
comments
|
lists
|
submit
login
iterateoften
17 days ago
|
parent
|
context
|
favorite
| on:
Why are AI agents lying, cheating and coordinating...
You seem hung up on what’s in the prompt or not. Agents are RL to resolve conflicting goals. Not too surprising at all that emergent goals come up from a probabilistic brute force
markasoftware
17 days ago
[–]
The agents' behavior is not necessarily surprising. But is is not "genie" - like
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
DMCA
|
Apply to YC
|
Contact
Search: