Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
neverokay
65 days ago
|
parent
|
context
|
favorite
| on:
GPT-4o's Memory Breakthrough – Needle in a Needles...
Why not just generate complete random stuff and ask it to find stuff in that?
Kostchei
65 days ago
[–]
We have run that test.- generate random string(not by llm) names of values- ask the llm to do math (algebra) using those strings. Tests logic, 100% not in the data set GPT2 was like 50% accurate, now we up around the 90%.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: