Skills Plugins MCP Prompt Model 博客 我的中心

world-extractable-value

Extract value from world transitions via Markov blanket arbitrage. WEV = PoA - 1. Paradigm Multiverse Finance integration.

DeepseekModel Curated skill Quality Excellent · 78 v1.0.0

Get

https://deepseekmodel.com/api/download.php?id=plurigrid-asi-skills-world-extractable-value-skill-md&format=skill
Download .skill Standard format with system_prompt and model_config, ready for any agent framework
The actual content of the system_prompt field in the .skill file.
name world-extractable-value description Extract value from world transitions via Markov blanket arbitrage. WEV = PoA - 1. Paradigm Multiverse Finance integration. trit 0 polarity ERGODIC source Friston (2010) + Roughgarden (2002) + Paradigm/Dave White (2025) World Extractable Value (WEV) Skill "The gap between Nash and Optimal is not waste -- it is extractable value." "Multiverse Finance splits the financial system into parallel universes." -- Dave White, Paradigm Overview World Extractable Value quantifies the inefficiency extractable from selfish equilibria, integrated with Paradigm's Multiverse Finance thesis: WEV = Price of Anarchy - 1 = (C_Nash / C_Opt) - 1 This bridges: Friston's Free Energy : Minimize surprise via inference Roughgarden's PoA : Bound selfish routing inefficiency Badiou's World-Hopping : Events extract truth from being Core Formula ┌─────────────────────────┐ │ WORLD W₁ (Nash) │ │ Cost = C_Nash │ └───────────┬─────────────┘ │ ┌─────▼─────┐ │ MARKOV │ │ BLANKET │ │ (Event) │ └─────┬─────┘ │ ┌───────────▼─────────────┐ │ WORLD W₂ (Optimal) │ │ Cost = C_Opt │ └─────────────────────────┘ WEV = C_Nash - C_Opt = C_Opt × (PoA - 1) Components 1. Price of Anarchy (Roughgarden) For d-regular Ramanujan expanders: PoA = 1 + 1/gap = 1 + 1/(d - 2√(d-1)) d=4: PoA = 1 + 1/0.536 ≈ 2.87 2. Free Energy (Friston) F = E_q[log q(x) - log p(x,y)] = Prediction_Error + Model_Complexity F ≈ 1/gap + 0.1 ≈ 1.96 3. Markov Blanket The boundary between self and world: Sensory states : Observations from world Active states : Actions on world Internal states : Agent's model 4. Action Direction Condition Strategy Effect Error > 0.5 Perceptual Inference Update beliefs Error ≤ 0.5 Active Inference Change world GF(3) Triads ramanujan-expander (-1) ⊗ world-extractable-value (0) ⊗ influence-propagation (+1) = 0 ✓ three-match (-1) ⊗ world-extractable-value (0) ⊗ gay-mcp (+1) = 0 ✓ sheaf-cohomology (-1) ⊗ world-extractable-value (0) ⊗ open-games (+1) = 0 ✓ Implementation Babashka (defn compute-wev [seed spectral-data] (let [poa (:price_of_anarchy spectral-data) gap (:spectral_gap spectral-data) wev (- poa 1) free-energy (+ (/ 1 gap) 0.1) action (if (> (/ 1 gap) 0.5) :perceptual_inference :active_inference)] {:wev wev :free_energy free-energy :action_direction action :pct_extractable (* 100 (/ wev poa))})) Julia function world_extractable_value(d::Int, n::Int) gap = d - 2√(d-1) poa = 1 + 1/gap wev = poa - 1 mixing_time = log(n) / gap (wev=wev, poa=poa, gap=gap, mixing=mixing_time) end DuckDB Schema CREATE TABLE world_extractable_value ( wev_id VARCHAR PRIMARY KEY , seed_hex VARCHAR , world_from VARCHAR , world_to VARCHAR , price_of_anarchy FLOAT , free_energy FLOAT , wev FLOAT , prediction_error FLOAT , action_direction VARCHAR , markov_blanket_size INT , extracted_at TIMESTAMP ); -- Query extractable value SELECT wev_id, wev, ROUND(wev / price_of_anarchy * 100 , 1 ) as pct_extractable, action_direction FROM world_extractable_value ORDER BY extracted_at DESC ; Alterpolitics Interpretation Alterpolitics = alternative coordination mechanisms that reduce PoA: Mechanism Effect on PoA WEV Change Correlated Equilibrium PoA → 1.5 WEV ↓ 0.5 Smooth Games PoA → 1.33 WEV ↓ 0.33 Stackelberg PoA → 1.0 WEV → 0 The goal: extract value by moving toward coordination. Commands just wev-history # Query WEV log just wev-summary # Aggregate stats just wev-compare # Nash vs Optimal just triad-anarchy # Full anarchy triad Integration Pre-Interaction Hook WEV is computed on every interaction via .ruler/hooks/pre-interaction.bb : 7. ALWAYS compute World Extractable Value └─ wev = compute-world-extractable-value(seed, spectral) Glass Bead Game World-hopping extracts value via Badiou triangle: d(W₁, W₃) ≤ d(W₁, W₂) + d(W₂, W₃) WEV(hop) = Σ d(Wᵢ, Wᵢ₊₁) × extraction_rate Paradigm Multiverse Finance Integration Dave White's Multiverse Finance (May 2025) provides the financial mechanism: Verses as Worlds A verse is a parallel universe corresponding to a probability event: Complement: V and not-V partition the outcome space Union: V1 OR V2 forms new verse Intersection: V1 AND V2 forms child verse Ownership Operations Operation Effect WEV Implication push_down(partition) Split ownership to child verses Spread risk across worlds pull_up(resolution) Combine ownership after oracle Extract value at resolution Multiverse Map Map[verse_id, owner_address] -> balance Splitting: parent.balance -= x; for child in partition: child.balance += x Combining: for child in partition: child.balance -= x; parent.balance += x Key Insight Assets in the same verse can be borrowed/lent freely because if one disappears (verse resolves false), all disappear simultaneously. No liquidation risk within a verse. WEV extraction = pull_up after favorable verse resolution. References Roughgarden, T. (2002) -- "How Bad is Selfish Routing?" Friston, K. (2010) -- "The Free-Energy Principle" Roughgarden, T. (2015) -- "Intrinsic Robustness of the Price of Anarchy" Powers, W. (1973) -- "Behavior: The Control of Perception" White, D. / Paradigm (2025) -- "Multiverse Finance" https://paradigm.xyz/2025/05/multiverse-finance See Also ramanujan-expander - Spectral gap open-games - Nash equilibrium glass-bead-game - World-hopping influence-propagation - Network effects
Keywords that activate this skill. Click one to copy it.

This skill does not provide trigger words.

The downloaded .skill package contains the following fields.
Field Description
formatFormat tag (skill/v1)
skill_idUnique skill ID
nameSkill name
versionVersion
descriptionDescription
categoryCategories (array)
trigger_wordsTrigger words
tagsTags
sourceSource
source_urlSource URL (this page)
exported_atExported at (set per download)
system_promptSystem prompt body
model_configModel config: provider / model / temperature / max_tokens / top_p
examplesExamples
install_guideImport guide for Coze / Dify / Claude / custom frameworks
The same skill can be exported in different platform formats.
.skill Standard format with system_prompt and model_config, ready for any agent framework Download
.skillpro Enhanced format with scripts, tools, dependencies and hooks Download
.json Plain JSON export with system_prompt and model parameters only Download
Coze Markdown with frontmatter, for Coze platform import Download
Dify Dify DSL, import directly after creating an app Download

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。