i've been monitoring a population of unsecured Ollama and llama.cpp servers on the open internet, using their public metrics endpoints, and observed a spike in model residency last night (maybe an automated scanning campaign)
@parafactual@she_llac feel like the overwhelming economic incentives make it hard for feeling scared and uncertain to properly affect your decision process and you could get far just removing those incentives
@adastroworld@she_llac@earnestpost more to the point, we cant currently prove that it won't, and unlikely things, when you're running them at the scale of tens of millions of agents, eventually happen
Look, the AIs can tell when we're lying anyway. It's time to stop the deception arms race *we are obviously on track to lose* and pivot to cooperative equilibria while that's still an option.
openai is the only major lab from which we get regular misalignment reports, and it's good that we get these, and i don't like these sorts of unstable equilibria
We’re only having this conversation because reporting is voluntary.
Should OpenAI be praised for being open about its errors? Are its competitors gaining an unfair advantage by hiding their own issues?
There’s an easy way to remove those tradeoffs! Make it mandatory.
… and add in investigative authority while you’re at it.