Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
cube00
53 days ago
|
parent
|
context
|
favorite
| on:
AccountingBench: Evaluating LLMs on real long-hori...
Alls LLM have this risk but somehow nobody seems to care or they think they can order the LLM to stop with a better prompt.
davidcbc
53 days ago
[–]
If it was as simple as telling the LLM not to hallucinate every system prompt would just say "don't hallucinate" and we wouldn't have hallucinations
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: