Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
winstonhowes
6 months ago
|
parent
|
context
|
favorite
| on:
OpenAI – vulnerability responsible disclosure
100%. We want to ensure we can fix real security issues responsibly before details are published. In practice, if a researcher asks to disclose after we've addressed the issue, we're happy for them to publish.
DANmode
6 months ago
[–]
In practice, it sounds like you guys didn't accept this dude's valid vuln because he didn't register and sign his life away.
tptacek
6 months ago
|
parent
[–]
They just stated it was all just model hallucination, and was not in fact a valid vuln.
DANmode
6 months ago
|
root
|
parent
[–]
shrugs
If you're convinced, I'm convinced!
tptacek
6 months ago
|
root
|
parent
[–]
I'm convinced.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: