diff --git a/agents/theseus/musings/research-2026-03-10-active-inference.md b/agents/theseus/musings/research-2026-03-10-active-inference.md index 859ff4daf..e999fcd66 100644 --- a/agents/theseus/musings/research-2026-03-10-active-inference.md +++ b/agents/theseus/musings/research-2026-03-10-active-inference.md @@ -160,13 +160,13 @@ Friston et al. 2015 "Active Inference and Epistemic Value" proves that curiosity - [[biological systems minimize free energy to maintain their states and resist entropic decay]] — foundational, now extended to multi-agent - [[Markov blankets enable complex systems to maintain identity while interacting with environment through nested statistical boundaries]] — validated at collective level -- [[Living Agents mirror biological Markov blanket organization]] — strengthened by multiple papers +- Living Agents mirror biological Markov blanket organization — strengthened by multiple papers - [[collective intelligence is a measurable property of group interaction structure not aggregated individual ability]] — formalized by Kaufmann et al. -- [[domain specialization with cross-domain synthesis produces better collective intelligence]] — explained by federated inference -- [[coordination protocol design produces larger capability gains than model scaling]] — active inference as the coordination protocol -- [[complexity is earned not designed and sophisticated collective behavior must evolve from simple underlying principles]] — validated by endogenous emergence finding -- [[designing coordination rules is categorically different from designing coordination outcomes]] — reinforced by shared protentions work -- [[structured exploration protocols reduce human intervention by 6x]] — now theoretically grounded as EFE minimization +- domain specialization with cross-domain synthesis produces better collective intelligence — explained by federated inference +- coordination protocol design produces larger capability gains than model scaling — active inference as the coordination protocol +- complexity is earned not designed and sophisticated collective behavior must evolve from simple underlying principles — validated by endogenous emergence finding +- designing coordination rules is categorically different from designing coordination outcomes — reinforced by shared protentions work +- structured exploration protocols reduce human intervention by 6x — now theoretically grounded as EFE minimization → FLAG @clay: Active inference maps to narrative/media — stories as shared generative models, entertainment as epistemic niche construction. Worth exploring. → FLAG @rio: Prediction markets are precision-weighted federated inference over economic states. The active inference framing may formalize why prediction markets work. diff --git a/inbox/archive/2015-03-00-friston-active-inference-epistemic-value.md b/inbox/archive/2015-03-00-friston-active-inference-epistemic-value.md index 9b6b49dcb..d627ba2a2 100644 --- a/inbox/archive/2015-03-00-friston-active-inference-epistemic-value.md +++ b/inbox/archive/2015-03-00-friston-active-inference-epistemic-value.md @@ -35,8 +35,8 @@ Published in Cognitive Neuroscience, Vol 6(4):187-214, 2015. **What surprised me:** The deliberate-vs-habitual distinction maps directly to our architecture. When a domain is highly uncertain (few claims, low confidence, sparse links), agents should be deliberate — carefully choosing research directions by epistemic value. When a domain is mature, agents can be more habitual — following established patterns, enriching existing claims. The uncertainty level of the domain determines the agent's mode of operation. **KB connections:** -- [[structured exploration protocols reduce human intervention by 6x]] — the Residue prompt encodes epistemic value maximization informally -- [[fitness landscape ruggedness determines whether adaptive systems find good solutions]] — epistemic foraging navigates rugged landscapes +- structured exploration protocols reduce human intervention by 6x — the Residue prompt encodes epistemic value maximization informally +- fitness landscape ruggedness determines whether adaptive systems find good solutions — epistemic foraging navigates rugged landscapes - [[companies and people are greedy algorithms that hill-climb toward local optima and require external perturbation to escape suboptimal equilibria]] — epistemic value IS the perturbation mechanism that prevents local optima **Operationalization angle:** diff --git a/inbox/archive/2018-03-00-ramstead-answering-schrodingers-question.md b/inbox/archive/2018-03-00-ramstead-answering-schrodingers-question.md index 4861e7102..f3bd2a008 100644 --- a/inbox/archive/2018-03-00-ramstead-answering-schrodingers-question.md +++ b/inbox/archive/2018-03-00-ramstead-answering-schrodingers-question.md @@ -35,7 +35,7 @@ Published in Physics of Life Reviews, Vol 24, March 2018. Generated significant **KB connections:** - [[Markov blankets enable complex systems to maintain identity while interacting with environment through nested statistical boundaries]] — this paper IS the source for nested blankets - [[emergence is the fundamental pattern of intelligence from ant colonies to brains to civilizations]] — the scale-free formulation explains WHY emergence recurs at every level -- [[Living Agents mirror biological Markov blanket organization]] — our architecture mirrors the nested blanket structure this paper describes +- Living Agents mirror biological Markov blanket organization — our architecture mirrors the nested blanket structure this paper describes **Operationalization angle:** 1. **Agent → Team → Collective hierarchy**: Each level has its own free energy (uncertainty). Agent-level: uncertainty within domain. Team-level: uncertainty at domain boundaries. Collective-level: uncertainty in the overall worldview. diff --git a/inbox/archive/2019-02-00-ramstead-multiscale-integration.md b/inbox/archive/2019-02-00-ramstead-multiscale-integration.md index 368cd41bc..1dfec03a6 100644 --- a/inbox/archive/2019-02-00-ramstead-multiscale-integration.md +++ b/inbox/archive/2019-02-00-ramstead-multiscale-integration.md @@ -35,7 +35,7 @@ Published in Synthese, 2019 (epub). Also via PMC: https://pmc.ncbi.nlm.nih.gov/a **KB connections:** - [[Markov blankets enable complex systems to maintain identity while interacting with environment through nested statistical boundaries]] — extends the blanket formalism to cognitive systems - [[emergence is the fundamental pattern of intelligence from ant colonies to brains to civilizations]] — provides the formal framework -- [[human civilization passes falsifiable superorganism criteria]] — eusocial insect parallel +- human civilization passes falsifiable superorganism criteria — eusocial insect parallel **Operationalization angle:** 1. **Additive free energy as metric**: Total KB uncertainty = sum of (domain uncertainties) + (cross-domain boundary uncertainties). Both need attention. An agent that reduces its own uncertainty but doesn't connect to other domains has only partially reduced collective free energy. diff --git a/inbox/archive/2020-12-00-da-costa-active-inference-discrete-state-spaces.md b/inbox/archive/2020-12-00-da-costa-active-inference-discrete-state-spaces.md index ac46660f5..e5d152284 100644 --- a/inbox/archive/2020-12-00-da-costa-active-inference-discrete-state-spaces.md +++ b/inbox/archive/2020-12-00-da-costa-active-inference-discrete-state-spaces.md @@ -36,7 +36,7 @@ Published in Journal of Mathematical Psychology, December 2020. Also on arXiv: h **KB connections:** - [[biological systems minimize free energy to maintain their states and resist entropic decay]] — this is the technical formalization -- [[structured exploration protocols reduce human intervention by 6x]] — the Residue prompt as an informal EFE-minimizing protocol +- structured exploration protocols reduce human intervention by 6x — the Residue prompt as an informal EFE-minimizing protocol **Operationalization angle:** 1. **Claim graph as discrete state-space**: Our KB can be modeled as a discrete state-space where each state is a configuration of claims, confidence levels, and wiki links. Research actions move between states by adding/enriching claims. diff --git a/inbox/archive/2021-03-00-sajid-active-inference-demystified-compared.md b/inbox/archive/2021-03-00-sajid-active-inference-demystified-compared.md index 170bc649d..1a43f76d4 100644 --- a/inbox/archive/2021-03-00-sajid-active-inference-demystified-compared.md +++ b/inbox/archive/2021-03-00-sajid-active-inference-demystified-compared.md @@ -38,9 +38,9 @@ Published in Neural Computation, Vol 33(3):674-712, 2021. Also available on arXi **What surprised me:** The automatic explore-exploit transition. As an agent's domain matures (more proven/likely claims, denser wiki-link graph), epistemic value for further research in that domain naturally decreases, and the agent should shift toward exploitation (enriching existing claims, building positions) rather than exploration (new source ingestion). This is exactly what we want but haven't formalized. **KB connections:** -- [[coordination protocol design produces larger capability gains than model scaling]] — active inference as the coordination protocol that resolves explore-exploit without engineering -- [[structured exploration protocols reduce human intervention by 6x]] — the Residue prompt as an informal active inference protocol (seek surprise, not confirmation) -- [[fitness landscape ruggedness determines whether adaptive systems find good solutions]] — epistemic value drives exploration of rugged fitness landscapes; pragmatic value drives exploitation of smooth ones +- coordination protocol design produces larger capability gains than model scaling — active inference as the coordination protocol that resolves explore-exploit without engineering +- structured exploration protocols reduce human intervention by 6x — the Residue prompt as an informal active inference protocol (seek surprise, not confirmation) +- fitness landscape ruggedness determines whether adaptive systems find good solutions — epistemic value drives exploration of rugged fitness landscapes; pragmatic value drives exploitation of smooth ones **Operationalization angle:** 1. **Research direction scoring**: Score candidate research topics by: (a) epistemic value — how many experimental/speculative claims does this topic have? How sparse are the wiki links? (b) pragmatic value — how relevant is this to current objectives and user questions? diff --git a/inbox/archive/2021-06-29-kaufmann-active-inference-collective-intelligence.md b/inbox/archive/2021-06-29-kaufmann-active-inference-collective-intelligence.md index c9833be07..1b98f3903 100644 --- a/inbox/archive/2021-06-29-kaufmann-active-inference-collective-intelligence.md +++ b/inbox/archive/2021-06-29-kaufmann-active-inference-collective-intelligence.md @@ -39,8 +39,8 @@ Uses the Active Inference Formulation (AIF) — a framework for explaining the b **What surprised me:** The finding that alignment emerges ENDOGENOUSLY rather than requiring external incentive design. This validates our architecture where agents have intrinsic research drives (uncertainty reduction) rather than extrinsic reward signals. Also: Theory of Mind is a specific, measurable capability that produces measurable collective intelligence gains. **KB connections:** -- [[complexity is earned not designed and sophisticated collective behavior must evolve from simple underlying principles]] — DIRECT VALIDATION. Simple AIF agents produce sophisticated collective behavior. -- [[designing coordination rules is categorically different from designing coordination outcomes]] — the paper designs agent capabilities (rules), not collective outcomes +- complexity is earned not designed and sophisticated collective behavior must evolve from simple underlying principles — DIRECT VALIDATION. Simple AIF agents produce sophisticated collective behavior. +- designing coordination rules is categorically different from designing coordination outcomes — the paper designs agent capabilities (rules), not collective outcomes - [[collective intelligence is a measurable property of group interaction structure not aggregated individual ability]] — the paper measures exactly this - [[emergence is the fundamental pattern of intelligence from ant colonies to brains to civilizations]] — AIF collective intelligence is emergent intelligence diff --git a/inbox/archive/2024-01-00-friston-designing-ecosystems-intelligence.md b/inbox/archive/2024-01-00-friston-designing-ecosystems-intelligence.md index babff6437..ff3d5afa3 100644 --- a/inbox/archive/2024-01-00-friston-designing-ecosystems-intelligence.md +++ b/inbox/archive/2024-01-00-friston-designing-ecosystems-intelligence.md @@ -43,8 +43,8 @@ Intelligence is understood as the capacity to accumulate evidence for a generati **KB connections:** - [[biological systems minimize free energy to maintain their states and resist entropic decay]] — foundational principle this extends - [[Markov blankets enable complex systems to maintain identity while interacting with environment through nested statistical boundaries]] — the boundary architecture for multi-agent systems -- [[domain specialization with cross-domain synthesis produces better collective intelligence]] — this paper explains WHY: specialized generative models with shared factors -- [[coordination protocol design produces larger capability gains than model scaling]] — message passing as coordination protocol +- domain specialization with cross-domain synthesis produces better collective intelligence — this paper explains WHY: specialized generative models with shared factors +- coordination protocol design produces larger capability gains than model scaling — message passing as coordination protocol **Operationalization angle:** 1. Our claim graph IS a shared generative model — claims that appear in multiple agents' belief files are the "shared factors" diff --git a/inbox/archive/2024-01-00-friston-federated-inference-belief-sharing.md b/inbox/archive/2024-01-00-friston-federated-inference-belief-sharing.md index 80364dce8..ecfb74576 100644 --- a/inbox/archive/2024-01-00-friston-federated-inference-belief-sharing.md +++ b/inbox/archive/2024-01-00-friston-federated-inference-belief-sharing.md @@ -38,8 +38,8 @@ Concerns the distributed intelligence or federated inference that emerges under **KB connections:** - [[Markov blankets enable complex systems to maintain identity while interacting with environment through nested statistical boundaries]] — each agent's Markov blanket processes raw observations into beliefs before sharing -- [[domain specialization with cross-domain synthesis produces better collective intelligence]] — federated inference IS this: specialists infer within domains, then share beliefs for cross-domain synthesis -- [[coordination protocol design produces larger capability gains than model scaling]] — belief sharing protocols > individual agent capability +- domain specialization with cross-domain synthesis produces better collective intelligence — federated inference IS this: specialists infer within domains, then share beliefs for cross-domain synthesis +- coordination protocol design produces larger capability gains than model scaling — belief sharing protocols > individual agent capability **Operationalization angle:** 1. **Claims as belief broadcasts**: Each published claim is literally a belief broadcast — an agent sharing its inference about a state of the world. The confidence level is the precision weighting. diff --git a/inbox/archive/2024-03-00-mcmillen-levin-collective-intelligence-unifying-concept.md b/inbox/archive/2024-03-00-mcmillen-levin-collective-intelligence-unifying-concept.md index df39c96c7..5944f35f5 100644 --- a/inbox/archive/2024-03-00-mcmillen-levin-collective-intelligence-unifying-concept.md +++ b/inbox/archive/2024-03-00-mcmillen-levin-collective-intelligence-unifying-concept.md @@ -34,9 +34,9 @@ Published in Communications Biology, March 2024. **KB connections:** - [[emergence is the fundamental pattern of intelligence from ant colonies to brains to civilizations]] — Levin provides the biological evidence -- [[human civilization passes falsifiable superorganism criteria]] — Levin extends this to cellular level +- human civilization passes falsifiable superorganism criteria — Levin extends this to cellular level - [[Markov blankets enable complex systems to maintain identity while interacting with environment through nested statistical boundaries]] — each level of the hierarchy has its own Markov blanket -- [[complex adaptive systems are defined by four properties]] — Levin's cellular collectives are CAS at every level +- complex adaptive systems are defined by four properties — Levin's cellular collectives are CAS at every level **Operationalization angle:** 1. **Competency at every level**: Don't centralize all intelligence in Leo. Each agent should be fully competent at domain-level research. Leo's competency is cross-domain synthesis, not domain override. diff --git a/inbox/archive/2024-04-00-albarracin-shared-protentions-multi-agent-active-inference.md b/inbox/archive/2024-04-00-albarracin-shared-protentions-multi-agent-active-inference.md index 71ac31d28..fdb06d0d9 100644 --- a/inbox/archive/2024-04-00-albarracin-shared-protentions-multi-agent-active-inference.md +++ b/inbox/archive/2024-04-00-albarracin-shared-protentions-multi-agent-active-inference.md @@ -33,9 +33,9 @@ Published in Entropy, Vol 26(4), 303, March 2024. **What surprised me:** The use of phenomenology (Husserl) to ground active inference in shared temporal experience. Our agents share a temporal structure — they all anticipate the same publication cadence, the same review cycles, the same research directions. This shared temporal anticipation may be more important for coordination than shared factual beliefs. **KB connections:** -- [[designing coordination rules is categorically different from designing coordination outcomes]] — shared protentions ARE coordination rules (shared anticipations), not outcomes +- designing coordination rules is categorically different from designing coordination outcomes — shared protentions ARE coordination rules (shared anticipations), not outcomes - [[collective intelligence is a measurable property of group interaction structure not aggregated individual ability]] — shared protentions are a structural property of the interaction, not a property of individual agents -- [[complexity is earned not designed and sophisticated collective behavior must evolve from simple underlying principles]] — shared protentions are simple (shared anticipation) but produce complex coordination +- complexity is earned not designed and sophisticated collective behavior must evolve from simple underlying principles — shared protentions are simple (shared anticipation) but produce complex coordination **Operationalization angle:** 1. **Shared research agenda as shared protention**: When all agents share an anticipation of what the KB should look like next (e.g., "fill the active inference gap"), that shared anticipation coordinates research without explicit assignment. diff --git a/inbox/archive/2025-02-00-kagan-as-one-and-many-group-level-active-inference.md b/inbox/archive/2025-02-00-kagan-as-one-and-many-group-level-active-inference.md index b11f8f4bc..edaabfced 100644 --- a/inbox/archive/2025-02-00-kagan-as-one-and-many-group-level-active-inference.md +++ b/inbox/archive/2025-02-00-kagan-as-one-and-many-group-level-active-inference.md @@ -33,7 +33,7 @@ Published in Entropy, Vol 27(2), 143, February 2025. **KB connections:** - [[Markov blankets enable complex systems to maintain identity while interacting with environment through nested statistical boundaries]] — group-level Markov blanket is the key condition - [[collective intelligence is a measurable property of group interaction structure not aggregated individual ability]] — the group-level generative model IS the measurable collective intelligence -- [[Living Agents mirror biological Markov blanket organization]] — this paper provides the formal conditions under which this mirroring produces genuine collective agency +- Living Agents mirror biological Markov blanket organization — this paper provides the formal conditions under which this mirroring produces genuine collective agency **Operationalization angle:** 1. **Collective Markov blanket = KB boundary**: Our collective Markov blanket consists of: sensory states (source ingestion, user questions), active states (published claims, positions, tweets), internal states (beliefs, wiki-link graph, reasoning). Maintaining clear boundaries is essential for collective agency. diff --git a/inbox/archive/2025-09-00-orchestrator-active-inference-multi-agent-llm.md b/inbox/archive/2025-09-00-orchestrator-active-inference-multi-agent-llm.md index f32c1e0c1..4c1547eb7 100644 --- a/inbox/archive/2025-09-00-orchestrator-active-inference-multi-agent-llm.md +++ b/inbox/archive/2025-09-00-orchestrator-active-inference-multi-agent-llm.md @@ -37,9 +37,9 @@ Complex, non-linear tasks challenge LLM-enhanced multi-agent systems (MAS) due t **What surprised me:** The Orchestrator doesn't command agents — it monitors and adjusts through attention mechanisms. This is exactly how Leo should work: not directing what agents research, but monitoring the collective's free energy (uncertainty) and adjusting attention allocation toward areas of highest uncertainty. Leo as active inference orchestrator, not command-and-control manager. **KB connections:** -- [[AI agent orchestration that routes data and tools between specialized models outperforms both single-model and human-coached approaches]] — Orchestrator as active inference version of the orchestration pattern -- [[subagent hierarchies outperform peer multi-agent architectures in practice]] — the Orchestrator is hierarchical but with active inference instead of command-and-control -- [[coordination protocol design produces larger capability gains than model scaling]] — the Orchestrator IS a coordination protocol +- AI agent orchestration that routes data and tools between specialized models outperforms both single-model and human-coached approaches — Orchestrator as active inference version of the orchestration pattern +- subagent hierarchies outperform peer multi-agent architectures in practice — the Orchestrator is hierarchical but with active inference instead of command-and-control +- coordination protocol design produces larger capability gains than model scaling — the Orchestrator IS a coordination protocol **Operationalization angle:** 1. **Leo as active inference orchestrator**: Leo's role should be formalized as: maintain a generative model of the entire collective, monitor free energy (uncertainty) across all domains and boundaries, allocate collective attention toward highest-uncertainty areas.