Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
bluefirebrand
5 months ago
|
parent
|
context
|
favorite
| on:
Chain of thought monitorability: A new and fragile...
Deception requires intent to deceive. LLMs don't have intent to anything except respond to prompts
Incorrectness doesn't required intent to decieve. It's just being wrong
bee_rider
5 months ago
[–]
That’s what I think as well, but I’m curious about the alternative perspective.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Incorrectness doesn't required intent to decieve. It's just being wrong