Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jbstack
3 months ago
|
parent
|
context
|
favorite
| on:
An LLM is a lossy encyclopedia
Yes, I should have clarified that I was referring to memory of training data, not of conversations.
withinboredom
3 months ago
[–]
Training data also deteriorates quite quickly as the context gets longer.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: