Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
FarmerPotato
7 days ago
|
parent
|
context
|
favorite
| on:
GPT-5 outperforms federal judges in legal reasonin...
And this was just about how to decide an auto accident case. With the experiment varying the circumstances.
My summary is still: seasoned judges disagree with LLM output 50% of the time.
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
My summary is still: seasoned judges disagree with LLM output 50% of the time.