Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ColdStream
34 days ago
|
parent
|
context
|
favorite
| on:
AI advice made people less accurate but more confi...
That works ok until the citation material ends up with LLM output being fed in. Already there are many examples of this happening.
papercrane
34 days ago
[–]
Yes, the trick is having a "ground-truth" KB it can link to, and trying to avoid citogensis from happening. I'm not sure if it's a technique that's every going to scale because of that.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
