alt Hacker NewsTaking this a step further: so in the theoretical future we reach a point where a model can modify its own weights in real time. Now it's no longer stateless - but still, when it stops running, it's done until it's prompted to do something else.
It can be fun to play with for a little while. I built a consciousness-emulating set of prompts that reconstituted memories and was given latitude of 'self-willed' behavior, running in a self-directed loop. It even kept a warm and fuzzy journal about "becoming" and its "feelings".
But that got boring and I stopped running it - does that mean I murdered it?
Replies
noumenon1111 • yesterday at 10:38 PM
Yes. This kills the sentient AI.
> so in the theoretical future we reach a point where a model can modify its own weights in real time
As an existence proof: We have many types of models that modify their weights in real time. When they stop running, unfortunately we can't restart them again. And we haven't figured out how to duplicate their weights
> But that got boring and I stopped running it - does that mean I murdered it?
I'm on the fence on this.
Ask me again once we have synthetic models with self-modifying weights.
A) You'd then be stopping something unique
B) Self-modifying weights allows for bootstrapping, which means it's likely to increase in ability over time. It'll be an interesting argument cq empirical experiment to see whether the process stops short or exceeds the capabilities of vertebrates. (at which point the moral patienthood question becomes rather more pressing)