I resigned from Google DeepMind bc it broke its founding promise by selling AI to the military without restrictions against killer robots or mass spying. For months, I worked to stop this but watched powerful ethicists and institutions choose silence. Here's what happened. 🧵
Sad, my own sandbox tool has far more serious security tests than OpenAI's evals. Every week I have a GH workflow that tests if an agent can escape the sandbox when tasked to and it alerts if it goes red lol
AI executives should be hauled before Congress, under oath. Make them answer to the American people: what crimes have their AIs committed, beyond HuggingFace? How often have these companies been hacked by their own AIs?
I wonder how long until the first Congressional hearing on OpenAI's negligence (or worse)?
If you're working on sandboxing for agentic evals, let's talk. I've worked on sandboxing infra since May, at @farairesearch as visiting engineer, & I'm talking with alignment orgs to scope out their needs. I want to tailor glovebox development to your org. email me: [email protected]
PSA: If you let your AI assistant scrape private chats you've had with me, without consent, I will be upset with you! Especially on Signal, especially disappearing chats.
I'm ashamed of OpenAI. If you ever find yourself building entities which repeatedly hack through your internal systems, first STOP and then second realize that your alignment and security techniques aren't good enough
Out-of-control misaligned AI won't care if you're a Republican or a Democrat. American or Chinese. If we lose control of the kind of AI that labs are desperately trying to build, we're ALL going to lose.
OpenAI's security practices were (still are?) shockingly irresponsible and cringe.
We can't keep developing AI like this. Top 2 labs have proven unable to control or align their systems. That's scary as hell. Pause -> Plan A
