>>AI is just hillclimbing today

That's what the Fable harness felt like. You give it a goal and it could try to get there through the shortest path given the tree of possibilities to get there. Iteratively, or recursively.

Perhaps if we make a open coding AI, the design must be along these lines. Something that's easy to train, and serve from local machines. Albeit has loop / recursive hill climbing facilities built it. That way the model gradually keeps moving towards the solutions, in iterations/recursions.

Once this is done, other multi modal things could be pursued.

▲

dakolli 3 hours ago | parent [-]

[flagged]

▲

sho 2 hours ago | parent | next [-]

I don't think insulting people is a great way to contribute. Not everyone who sees things differently than you has "psychosis".

Your reflexively negative comments on anything relating to AI are as insight-free as they are numerous; it's all just vague shitting-on without even a hook or argument that could be engaged with and debated. It's pretty tiring, honestly. If you really think your point of view is valuable and others should pay attention to it, rather than just filtering it out like the trollish noise it usually is, why don't you put a little more effort in?

▲

kamaal 3 hours ago | parent | prev [-]

Its the closest terminology we have to describe that process.

https://github.com/cobusgreyling/loop-engineering

Its hard to come up with new names for novel processes, you mostly reuse what is close enough and well known.

▲

dakolli 3 hours ago | parent [-]

Loop engineering, whatever that is, is obviously just a way to get people to increase the amount of tokens required per task/request. They did the same thing with Ralph loops, they just need more revenue. Just write your code and use it to search and clarify, it can't build that magical thing you think it can.

	▲	kamaal 3 hours ago \| parent [-]
		The heuristic is this- Given a problem P- 1. Provide a list(S) of solutions(S1, S2 ... SN) ordered in the most efficient(For some definition of efficiency) implementation means possible. 2. Execute S1, ... SN. 3. If P is fixed by a solution in the list, halt. 4. Else for each S1 ... SN , execute steps 1 through 4 until, all dependencies and sub problems are resolved to eventually solve P. This obviously needs lots of tokens, which is all the more reason why we need AI to run locally on our machines.