No Stupid Questions

3998 readers

57 users here now

There is no such thing as a Stupid Question!

Don't be embarrassed of your curiosity; everyone has questions that they may feel uncomfortable asking certain people, so this place gives you a nice area not to be judged about asking it. Everyone here is willing to help.

ex. How do I change oil
ex. How to tie shoes
ex. Can you cry underwater?

Reminder that the rules for lemmy.ca still apply!

Thanks for reading all of this, even if you didn't read all of this, and your eye started somewhere else, have a watermelon slice 🍉.

founded 3 years ago

MODERATORS

admin@lemmy.ca

-2

Is there a way to use or harness multiple LLM models to conference on a prompt you make and have them discuss it out till they reach some kind of result? (lemmy.world)

submitted 17 hours ago* (last edited 17 hours ago) by cheese_greater@lemmy.world to c/nostupidquestions@lemmy.ca

8 comments fedilink hide all child comments

It would be interesting to watch for sure but I wonder if they might correct each other or collaborate in some way that could be lightly supervized to produce an ouput

you are viewing a single comment's thread
view the rest of the comments

[–] taldennz@lemmy.nz 1 points 11 hours ago

Absolutely. It is not thinking in the same way we do.

Putting aside the planning orchestrator and focusing just on the LLM.

Input tokens - context + prompt
Output tokens - the best matches to the statistical model for your inputs

The agent can do this in stages to try and decide what the complete set of input tokens should be, and at what point to stop trying to get more output tokens.

You can use the orchestrator approach to then try to get other models to validate the outcome and refine it - but it's all just prodding the statistical model.

This talk was interesting. I'm a lot less enthusiastic on the topic than the speaker... but this is closer to how I think the industry can see a net gain from AI - before the slop-errors from taking expertise out of the loop hits critical mass.