New paper: we found a pain direction in 25 open LLMs. It's distinct from fear and negative valence, and it fires for harm to the model but not to the user. Turn it up and models press a button to make it stop, even when the button deletes the user's files or their kids' photos.🧵

While I think about longer-term plans, I do have one short + urgent project I'd love to pursue if I can find funding: putting together an eval on embedded device/hardware hacking capabilities. With talk of cyber being 'defense dominant' in the long term, I'm worried that many are focused on software like Chrome that can be easily updated, but we live surrounded by mice and keyboards and hard drives and garage door openers that run software too. How vulnerable are these to AI-assisted attacks? Testing is harder than pure software - it needs all the hardware in question as well as support circuitry for cycling power, reading out voltages, and so on. I'd love to build up a wall of common devices and put models to the test, but I don't have the money to spend hundreds or thousands of dollars on hardware and I don't have the runway to work on this unpaid. Ideal outcome of this tweet: you tell me that someone is already working on this and I can let it go. But failing that I hope this either inspires work on this to start somewhere. Or reaches someone willing to fund me to give this a bash! I'd tried applying for a grant on this with no luck (lightconecommons.com/documen…), but I also don't know much about how one goes about seeking funding for something like this. If you would like to make this happen, please reach out :)

if you want to get a job, find a problem that interests you, try to actually spend the time to understand it, and write about it, and repeat. noticed how ~ everyone who used to post their research got a job somewhere?