Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
amelius
7 months ago
|
parent
|
context
|
favorite
| on:
LLMs get lost in multi-turn conversation
I suppose that the chain-of-thought style of prompting that is used by AI chat applications internally also breaks down because of this phenomenon.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: