Isn’t this the same as just telling it the goal directly but with more steps?
Yeah, I strongly feel this kind of stuff will just fall away as models get smarter and have a longer and longer viable time horizon per task.
Prompt Engineering, OpenClaw, Ralphing (remember that?) have all fallen already.
Yeah, I strongly feel this kind of stuff will just fall away as models get smarter and have a longer and longer viable time horizon per task.
Prompt Engineering, OpenClaw, Ralphing (remember that?) have all fallen already.