AGI AI Agent

[russdanner]

Not exactly an AGI programming topic -- but this is an AGIle AGI engine project. Just thought I would share how it's going.




<iframe width="560" height="315" src="https://www.youtube.com/embed/e42I2bP0F6g?si=KHspXF3RJoZHh3FN" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>

[AGKorson]

That's pretty cool!

You should give your project a name. Might I suggest Artificial Larry - 'AL'. (An homage to Larry's creator!)

So how do you expect AL to improve? Do you have to change the interface, or is it just a matter of letting the AI just keep trying? As the AI learns, where does its new knowledge get stored? If someone else was to try the same thing, would the AI remember what it learned from your project?

[lskovlun]

With SCI (1 and later), you'd get pathfinding for free. One less problem to solve.