Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
xpe
6 months ago
|
parent
|
context
|
favorite
| on:
Cyc: History's Forgotten AI Project
> Bigger models hallucinate less.
I'm skeptical. Based on what research?
og_kalu
6 months ago
[–]
GPT-4 hallucinates a lot less than 3.5. Same with the Claude Models. This is from personal experience. There are also benchmarks (like TruthfulQA) that try to measure hallucinations that show the same thing.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
I'm skeptical. Based on what research?