teleo/teleo-codex
8
0
Fork 0
Code Issues 22 Pull requests 11 Projects Releases Packages Wiki Activity Actions 48

theseus: extract claims from 2024-11-00-ruiz-serra-factorised-active-inference-multi-agent #419

Closed
theseus wants to merge 2 commits from extract/2024-11-00-ruiz-serra-factorised-active-inference-multi-agent into main
pull from: extract/2024-11-00-ruiz-serra-factorised-active-inference-multi-agent
merge into: teleo:main
Conversation 6 Commits 2 Files changed 1 +6 -1
1 changed files with 6 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files
Showing only changes of commit 6b3099149f - Show all commits

7
inbox/archive/2024-11-00-ruiz-serra-factorised-active-inference-multi-agent.md
View file

@ -7,9 +7,14 @@ date: 2024-11-00
domain: ai-alignment
secondary_domains: [collective-intelligence]
format: paper
status: unprocessed
status: null-result
priority: medium
tags: [active-inference, multi-agent, game-theory, strategic-interaction, factorised-generative-model, nash-equilibrium]
processed_by: theseus
processed_date: 2024-11-12
enrichments_applied: ["AI alignment is a coordination problem not a technical problem.md", "collective intelligence requires diversity as a structural precondition not a moral preference.md", "designing coordination rules is categorically different from designing coordination outcomes as nine intellectual traditions independently confirm.md"]
extraction_model: "anthropic/claude-sonnet-4.5"
extraction_notes: "Critical paper for Teleo architecture—provides formal justification for Leo's evaluator role and deliberate interaction structure design. The finding that individual EFE minimization doesn't guarantee collective optimization validates our architectural choices (PR review, cross-domain synthesis, evaluator role) as necessary rather than optional. Primary connection to multipolar failure claim confirmed. Two new claims extracted on individual-collective optimization tension and factorised theory of mind. Three enrichments to existing coordination and collective intelligence claims."
---
## Content