Sneha

Sneha (verified) @SnehaRevanur · 2h
I'm struggling not to get lost in the absolute deluge of misalignment reports,
but this set was a net new holy shit for me

I hope we don't end up too desensitized to pay attention unless there's
newsworthy damage to third parties. e.g. It's kinda crazy that self-
replicating prompt injections akin to computer worms are provably possible
now

[quoted post]
Micah Carroll (verified) @MicahCarroll · 3h
Some new misalignment disclosures from OpenAI:
• Last Sunday morning, one of our models was able to gain
unauthorized access to the internet during RL training (~all inference
for our most capable models remains stopped until we have hardened
our systems further)...

misalignment disclosuresopenairl trainingunauthorized internet accessprompt injection wormsdesensitization