Arthur H

358 posts

Arthur H

Arthur H

@mpanzz

🏴‍☠️ – building granular : easy to build introspective environments for AI agents

europe Katılım Haziran 2011
1.4K Takip Edilen456 Takipçiler
Arthur H retweetledi
François Fleuret
François Fleuret@francoisfleuret·
Language should be a mere readout of a world-model-based reasoning. The only domain where language and world overlap is programming, no surprise this is where LLMs shine.
English
4
3
30
3.4K
Arthur H
Arthur H@mpanzz·
Until agents can reason about their own action space as first-class objects, they remain capable, but fragile when confronted with novelty or complexity
English
0
0
1
25
Arthur H
Arthur H@mpanzz·
If we go back to Jaynes, consciousness emerged when command-based behavior stopped being enough and we needed an internal model of their own decisions and possibilities In agentic AI, we may be at a similar point: lacking an introspectable model of the agent's environment
English
1
0
1
37