Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
flexagoon
64 days ago
|
parent
|
context
|
favorite
| on:
Codex starts encrypting sub-agent prompts
> How do you know that they don't train their models or append your prompts to add backdoors, or compromise your supply chain by including evil dependencies?
I read the code.
kbart
63 days ago
[–]
That's not bullet proof.
https://en.wikipedia.org/wiki/Underhanded_C_Contest
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
I read the code.