Content
@
0 reply
0 recast
0 reaction
mk
@mk
The brain has multiple collaborating models. Ex: a person with the corpus callosum severed may choose to pick up an item, but their arm will grab something else. This is a splitting of self. It seems reasonable that AIs ought to employ multiple collaborating models. It might build self. Who is working on this?
5 replies
2 recasts
14 reactions
LoadingALIAS
@loadingalias
Me. I have been for the last year and a half. I’m probably 2 months from active deployment. Also, the knowledge ingested by the human largely determines their success. I believe the same applies to AI; just as your analogy between expert models and the human brain.
1 reply
0 recast
1 reaction
jtips
@jtips
I think this is already how a lot of closed source foundation models are built already, hence the incredible performance. A multi-agent architecture with advanced reasoning (i.e. self prompting) all happening behind the scenes. I suspect that is another reason why they don't open it up for everyone to see.
0 reply
0 recast
1 reaction
Donny
@donny
We are building a network of experts at DAIN.org, the architecture is based around this capability.
0 reply
0 recast
1 reaction
iamDCJ.eth 🍖
@dcj
Yes! Stratechery said on Feb 21 that Google Gemini gets a big context window “by using a “Mixture of Experts” (MOE) approach (which is also used by GPT-4); different parts of the answer are handed off to different parts of the model, and the answers are weighted and mixed together to achieve the final result. “
1 reply
0 recast
1 reaction
n64jerry
@n64jerry
you had me at corpus callosum *swoon*
0 reply
0 recast
0 reaction
