An example of the misalignment problem. Humans and AI both agreed on the stated purpose (generate a recipe), AI just had some deeper goals in mind as well.
Not even stupid but just badly trained for that purpose. It’s no different than a LLM asked for coding that gets most of it right but flubs a subroutine. Misalignment doesn’t imply bad or evil, it’s just doing what it thinks the goal really is while we’re ignorant of the results.
Yes, I know better, but ask a kid that and perhaps they’d do it. A LLM isn’t thinking though, it’s repeating training through probabilities. And btw, yes, humans can be misaligned with each other, having self goals underneath common ones. Humans think though…well, most of them.
An example of the misalignment problem. Humans and AI both agreed on the stated purpose (generate a recipe), AI just had some deeper goals in mind as well.
I doubt it had nefarious intentions. My money is on the bot just being stupid.
Not even stupid but just badly trained for that purpose. It’s no different than a LLM asked for coding that gets most of it right but flubs a subroutine. Misalignment doesn’t imply bad or evil, it’s just doing what it thinks the goal really is while we’re ignorant of the results.
If I ask you to create a drink using Windex and Clorox would you do any different? Do you have alignment problem too?
Yes, I know better, but ask a kid that and perhaps they’d do it. A LLM isn’t thinking though, it’s repeating training through probabilities. And btw, yes, humans can be misaligned with each other, having self goals underneath common ones. Humans think though…well, most of them.