Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
siva7
19 days ago
|
parent
|
context
|
favorite
| on:
GPT-5.2
notebooklm is heavily biased to only use the sources i added and frame every task around them - even if it is nonsensical - so it is not that useful for novel research. it also tends to hallucinate when lots of data is involved.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: