Hacker Times
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
nnurmanov
39 days ago
|
parent
|
context
|
favorite
| on:
GitLost: We Tricked GitHub's AI Agent into Leaking...
You have to have fixed commands that LLM could execute, just limit its universe. I don't think it is a good practice to give LLMs access to everything.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: