Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
rs186
61 days ago
|
parent
|
context
|
favorite
| on:
The "confident idiot" problem: Why AI needs hard r...
We talk about "probability" here because the topic is hallucination, not getting different answers each time you ask the same question. Maybe you could make the output deterministic but does not help with the hallucination problem at all.
sweezyjeezy
61 days ago
[–]
Exactly - 'non-deterministic' is not an accurate diagnosis of the issue.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: