| ▲ | coffeebeqn a day ago | |
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? | ||