Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Grimblewald
9 months ago
|
parent
|
context
|
favorite
| on:
Fresh evidence of ChatGPT’s political bias: study
'non-verbal semantic frames vs individual words' ok i'd agree for things using lstm style architecture but that goes out the window with transformers.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: