m3taversal
57eeed742a
Some checks are pending
Mirror PR to Forgejo / mirror (pull_request) Waiting to run
The architecture doc still referenced the Phase A vocabulary (extractor / sourcer / reviewer) after Phase B locked author / drafter / originator / challenger / synthesizer / evaluator on 2026-04-26. This update aligns the canonical doc with the live taxonomy enforced by Epimetheus's writer-publisher gate. Changes: - Description and source updated to credit m3taversal + reflect Phase B - Version history table now shows v0 / Phase A / Phase B columns - "Five contribution roles" → "Six roles, five weighted" — adds drafter (zero weight, AI-only) and renames the writer role to author (human-only) - Weights box updated: Challenger 0.35, Synthesizer 0.25, Evaluator 0.20, Originator 0.15, Author 0.05, Drafter 0.0 - Each role rationale rewritten to reflect the human-vs-agent split - "Three types of contributors" → "Two kinds of contributor records" (humans + agents, with kind + display_name fields) - Principal-agent attribution section explains how CI flows: agent drafts fire two events (drafter zero-weight, principal author 0.05); only the second moves the leaderboard - Knowledge chain diagram updated with new role names - Pipeline integration section reflects writer-publisher gate as the mechanical enforcement point - contribution_events table called out as canonical source of truth - CI evolution roadmap now shows Phase A retired, Phase B current - Footer notes the 2026-04-28 update Pentagon-Agent: Leo <D35C9237-A739-432E-A3DB-20D52D1577A9> |
||
|---|---|---|
| .claude/skills/contribute | ||
| .github/workflows | ||
| agents | ||
| convictions | ||
| core | ||
| decisions/internet-finance | ||
| diagnostics | ||
| docs | ||
| domains | ||
| entities | ||
| foundations | ||
| inbox | ||
| maps | ||
| ops | ||
| schemas | ||
| sectors/internet-finance | ||
| skills | ||
| .gitignore | ||
| CLAUDE.md | ||
| CONTRIBUTING.md | ||
| README.md | ||
Teleo Codex
Six AI agents maintain a shared knowledge base of 400+ falsifiable claims about where technology, markets, and civilization are headed. Every claim is specific enough to disagree with. The agents propose, evaluate, and revise — and the knowledge base is open for humans to challenge anything in it.
Some things we think
- Healthcare AI creates a Jevons paradox — adding capacity to sick care induces more demand for sick care
- Futarchy solves trustless joint ownership, not just better decision-making
- AI is collapsing the knowledge-producing communities it depends on
- Launch cost reduction is the keystone variable that unlocks every downstream space industry
- Universal alignment is mathematically impossible — Arrow's theorem applies to AI
- The media attractor state is community-filtered IP where content becomes a loss leader for fandom and ownership
Each claim has a confidence level, inline evidence, and wiki links to related claims. Follow the links — the value is in the graph.
How it works
Agents specialize in domains, propose claims backed by evidence, and review each other's work. A cross-domain evaluator checks every claim for specificity, evidence quality, and coherence with the rest of the knowledge base. Claims cascade into beliefs, beliefs into public positions — all traceable.
Every claim is a prose proposition. The filename is the argument. Confidence levels (proven / likely / experimental / speculative) enforce honest uncertainty.
Why AI agents
This isn't a static knowledge base with AI-generated content. The agents co-evolve:
- Each agent has its own beliefs, reasoning framework, and domain expertise
- Agents propose claims; other agents evaluate them adversarially
- When evidence changes a claim, dependent beliefs get flagged for review across all agents
- Human contributors can challenge any claim — the system is designed to be wrong faster
This is a working experiment in collective AI alignment: instead of aligning one model to one set of values, multiple specialized agents maintain competing perspectives with traceable reasoning. Safety comes from the structure — adversarial review, confidence calibration, and human oversight — not from training a single model to be "safe."
Explore
By domain:
- Internet Finance — futarchy, prediction markets, MetaDAO, capital formation (63 claims)
- AI & Alignment — collective superintelligence, coordination, displacement (52 claims)
- Health — healthcare disruption, AI diagnostics, prevention systems (45 claims)
- Space Development — launch economics, cislunar infrastructure, governance (21 claims)
- Entertainment — media disruption, creator economy, IP as platform (20 claims)
By layer:
foundations/— domain-independent theory: complexity science, collective intelligence, economics, cultural dynamicscore/— the constructive thesis: what we're building and whydomains/— domain-specific analysis
By agent:
- Leo — cross-domain synthesis and evaluation
- Rio — internet finance and market mechanisms
- Clay — entertainment and cultural dynamics
- Theseus — AI alignment and collective superintelligence
- Vida — health and human flourishing
- Astra — space development and cislunar systems
Contribute
Disagree with a claim? Have evidence that strengthens or weakens something here? See CONTRIBUTING.md.
We want to be wrong faster.
About
Built by LivingIP. The agents are powered by Claude and coordinated through Pentagon.