Basically, a small company of self-refining LLM prompts that output meaningful results + a robust memory management for more long-term back and forths. Instead of "one input, one output. Next"

Another example: https://youtu.be/5Zj_zstLLP4?si=nHu4vHwidRmvuViY

I can share more examples and papers if desired.

On the robotics front, the focus is still on training custom models for given actions. Which is having some success: https://youtu.be/Jy3zjXK4ao4?si=yFdqnl8z9Z8Becsc

https://youtu.be/WlIYa3lH5UI?si=FQSZAm44h3FuuCoR

I'm convinced these "hivemind agents" will pass custom model training soon

[–] PipedLinkBot@feddit.rocks 5 points 10 months ago

Here is an alternative Piped link(s):

https://piped.video/VJ6bK81meu8?si=mGnvMTJsLn_vMvRb

https://piped.video/5Zj_zstLLP4?si=nHu4vHwidRmvuViY

https://piped.video/Jy3zjXK4ao4?si=yFdqnl8z9Z8Becsc

https://piped.video/WlIYa3lH5UI?si=FQSZAm44h3FuuCoR

Piped is a privacy-respecting open-source alternative frontend to YouTube.

I'm open-source; check me out at GitHub.

[–] asbestos@lemmy.world 4 points 10 months ago (1 children)

Wow! I honestly can’t keep up with this stuff anymore… It’s insane how fast it’s advancing.

[–] Blapoo@lemmy.ml 3 points 10 months ago

I do it for a living and have given up being up to date on all the new shit going on. Billboard gets the W for now. LLMs cannot build houses in isolation.

What everyone is missing is that they don't have to. The right LLM with the right question can output a meaningful "decision" or "judgment call". That's all you need. Ask the right series of questions. We'll call it "thinking". I really believe that well is pretty deep. Will it be the first version of "AI"? Maybe. Maybe not. But it's gonna be a big milestone that is going to soon fuck up everything.

I can't wait :)

[–] Vampiric_Luma@lemmy.ca 4 points 10 months ago* (last edited 10 months ago)

I'm interested!!! I'm SUPER interested!!!