Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
metalliqaz
86 days ago
|
parent
|
context
|
favorite
| on:
TimeCapsuleLLM: LLM trained only on data from 1800...
The discussion is about training an LLM on old text and then asking it about new concepts.
djwide
79 days ago
[–]
AlphaGo was trained on old games and then presented with a game it had never seen before. It came up with a move that a human would not have played.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
