Remix.run Logo
▲ shmolyneaux a day ago

I think it's reasonable that humans need to provide context for this, and situations like this, forever. The GP has a specific problem. The context of the problem exists in the real world, not something that the agent can search for. This isn't a "humans are still important" take. This is custom software for meeting the specific needs and preferences of an individual.

I fully agree with them that the easiest solution is to ask an agent for exactly what you want, and iterate from there. Evaluating and installing and learning off-the-shelf software is often more of a pain than doing it from scratch.

▲augment_me a day ago | parent [-]

What prevents a solution where you physically hook up the needed components and then type "/goal make this keyboard extension work"

And the same library is built without the "seed" or baseline?

▲zahlman a day ago | parent [-]

What does "work" mean? How should the agent know what UI you want? How should you know, until you try something out?

▲augment_me a day ago | parent [-]

Answering here for both of your comments:

1) If the UX/UI is important for you, the agent can have access to your other work, or to your other conversation and build your tool with that in mind. This is just another search space question. If you have a documented, predictable taste, the models can efficiently produce what you need.

My uni supervisor/professor used to complain about my slop papers, then I started generating them in his writing style by just pulling down all of his papers and blogs, and he doesn't mind it now.

2) In general, the LLMs are great for steering opinion. There is good research on steering political opinion with LLMs. Your taste and opinions can be formed by the LLMs to like the solution that it provides you.

▲zahlman 7 hours ago | parent [-]

I'm not sure you understand how much pure contempt for humanity you demonstrate with this line of argument, even if your premises were true (they really aren't; I've looked at those papers and the quality of research is immediately laughable — all you have to do is think about how they're claiming humans react to LLM output, and compare it to what is readily observable all around us). Suffice to say that if you're trying to convince people to use AI more freely then this is exactly counterproductive. You apparently take pride in deceiving others and imagine that a conflict between a human's opinion and an AI's work is irrelevant because the former can be molded to accept the latter.

AI exists to serve us. It is not even alive, and not conscious and not deserving of rights, never mind any kind of entitlement to overrule us.