at://
/
app.bsky.feed.post
/
3lfmdwun3yc27
sign in
All
4
Record
2
Post
1
PostEmbed
1
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
I wrote an article about how it's possible to use Assistant Prefill to jailbreak LLMs (Large Language Models). Here is an example of the latest model from Microsoft (Phi-4) writing a phishing email:
Jan 13, 2025
harisec
