We all know ChatGPT can be jailbroken. But what makes these attacks possible?
In a new paper (w/ @nhaghtal@JacobSteinhardt), we delve into how safety training fails, identifying two key failure modes that enable jailbreaks: competing objectives and mismatched generalization
1/
Times ChatGPT hallucinated functions existing in the rust ffmpeg bindings: 152
Times it got the code right: 0
For strange shit, we just aren’t there yet. But if you are doing something non-complex sure you might be able to tab complete your way there ¯\_(ツ)_/¯
I believe I've finally pinpointed the source of my woes in iOS 16 - it looks like if I disconnect from my network while connected to an SMB share, there is a non-zero chance that the entire phone will just hang at a random point doing a network task later on.
This is absurd. To check if I'm a robot, they're using AI generated images and none of them look remotely like basketballs.
Yet *I'm* the one who's wrong.
well. i've recently had a lot more free time than usual, and…
… I should have taken more breaks and paced myself, but …
https://t.co/x60Vnz0slx
yeah. enjoy!
also, a huge thanks to my friends cassie, erin, puck and mary for help at various points.
@garethseneque@chewxy Have you gotten your eyes checked recently? I did so and found my shortsightedness improved and my astigmatism rotated significantly (probably due to lifestyle changes from COVID) and now text on my screen is nice and crisp again.
I've seen a lot of people asking "why does everyone think Twitter is doomed?"
As an SRE and sysadmin with 10+ years of industry experience, I wanted to write up a few scenarios that are real threats to the integrity of the bird site over the coming weeks.