There was one guy commenting on my old post that stuck with me along the lines, what would you need for you to approve less. It first bothered me, but I kept it with me and I started thinking differently about my software and especially with Opus 5.5 + heavy linting and cleanup routines it seems sane to evolve to pipelinee engineering, but it also makes me feel that whatever I’m doing now is gonna be in the next model, because what I did yesterday is in the model now...
I had no idea that we there are SO many aesteroids that we keeping track of. How are we even doing that? How do we recognize one aesteroid from another?
I was at uni in 2005. A mate wanted to search for a book and wrote something like this in Google search "go to digital library and find me this book". We laughed at what he did back then, searched for "" in quotes and may be with filetype I dont remember and found the book.
I think about that lots of times when I google these days. That he wasn't wrong, was just asking it 15 years too early.
an interface goes from the programmer's concept to written code, transformed into a frontend for the programmer and the rest of humanity to prompt (verb); eventually the accumulated prompts from a programmer get brute-forced into design fundamentals like evolution in nature, or the frontend is designed to go around this (apple style UX).
I think they just mean the robot does the tasks autonomously without human intervention. The G1 is just the physical body, it still needs software to drive its decisions
Can you please explain what does it mean by bitter lesson in this context specifically? I keep seeing this term here. I know there is an article of the same title but I still don't understand.
Yup and I think these examples demonstrate just that. From my experience, both Claude and ChatGPT iterate over what they can see to build things like these. I don't think these examples are made without vision.
Aren't these the same thing, to some extent? I remember my music teacher told me, that as long as you can hear your false tones, she can teach you how to sing, no matter how bad you are at it. But if you can't hear it, she cannot help you.
AI is the same - as long as it can see well, it can tell the difference between what it outputs and what its supposed to. If you subtract the two, you have an error, and you can hill-climb on that.
> I have very little need to run Agents over night, as my throughput is limited by my approval.
> I really have no idea what to do with my agents over night.
reply