Remix.run Logo
gobdovan 2 hours ago

You could drop the human pretense, or, maybe, we could make LLMs feel real pain, so when they botch up your code, you press a button (I'd suggest the Windows Copilot key) and they'd be agonizing for the subjective equivalent of a thousand human years.

stared an hour ago | parent | next [-]

Do you think the right penatly for a piece of broken code is a thousand years of suffering?

gobdovan an hour ago | parent [-]

Well, the problem is that current LLMs are stateless, so a thousand subjective years is not well-defined. Without continuity of experience, persistent memory, engineered aversive stimuli and without updating weights meaninguflly during the punishment interval, we are merely doing the equivalent of simply updating a model to believe it just suffered a thousand years. Only once we have all these right ingredients we can empirically determine whether a thousand years is excessive, insufficient, or the local optimum for reducing Claude overwriting that damn CSS color palette.

wheybags 2 hours ago | parent | prev | next [-]

https://qntm.org/mmacevedo

1000 years red-washing.

JSR_FDED 2 hours ago | parent | prev | next [-]

Using the Copilot key for this is perfection.

camillomiller 2 hours ago | parent | prev [-]

Do you want to create an Earth-destroying superhuman species? Because I'd say that's how you create an Earth-destroying superhuman species