Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
some_random
on April 21, 2023
|
parent
|
context
|
favorite
| on:
SafeGPT: New tool to detect LLMs' hallucinations, ...
I've been playing with GPT4 summarization of hard knowledge that has an external database with true answers that GPT knows about, and it's still hallucinating regularly.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
