Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jslezak
on Aug 9, 2024
|
parent
|
context
|
favorite
| on:
GPT-4 LLM simulates people well enough to replicat...
They did this. Read the paper
abcgde
on Aug 11, 2024
[–]
Well, they looked at papers that weren't published as of the original model release. But GPT very likely had unannounced model updates. Is it not possible that many of the post 2021 papers were in the version of GPT they actually worked with?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: