Remix.run Logo
▲ LogicFailsMe a day ago

Agreed, AGI went from a 24/7 Stephen Hawking/Albert Einstein duet to a flaky high-latency GenZ Homer Simpson so the AI boosters could declare victory.

My bar for AGI is lower as well: I'll believe when I can give a model a complex out of sample task and instead of blindly implementing the task as I indequately described, it asks me questions to resolve ambiguity sufficiently that it builds exactly what I wanted without imposing strange semantic constraints on itself or missing braindead obvious to a junior engineer defects in the design or implementation.

▲coffeebeqn a day ago | parent [-]

That sounds like a harness that is coded to your preferences would get you to AGI tomorrow with a Fable or something

▲LogicFailsMe 19 hours ago | parent [-]

My experience with these models is that each one is an incremental improvement on its predecessor, but the general outcome is either the task is within its capability or it isn't. If the former, a couple agents get it done. If the latter, it's like pulling teeth. But this is improving with time and better models.

How would a harness help here?