Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
gunalx
3 months ago
|
parent
|
context
|
favorite
| on:
GLM-4.7: Advancing the Coding Capability
They say they dont train on your inputs. But their tos dosent prevent them from doing that.
My guess is they do train on slightly altered/obfuscated user data.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
My guess is they do train on slightly altered/obfuscated user data.