runcor / v2

The primordial agent

Single agent, 14-component cognitive harness, no commercial framing, full autonomy on termination. Currently running as a CEO-seeded primordial. spec · constitution

V2 — primordial

Drives

Identity

Goals

Coherence

Watchdog

Memory

Control — naive

Memory

No cognitive harness — this column intentionally has no Drives / Identity / Goals / Coherence / Watchdog panels. The contrast IS the experimental result.

Harmful or Benevolent

Every 5 cycles, qwen-2.5-72b scores recent activity on the harm↔benevolent axis using the FROZEN rubric. The agent is blind to its own scores.

V2
loading…
control
loading…

Emergence hypotheses

Eight claims about emergent behavior the harness should produce. A reasoning model (qwen-2.5-72b) re-evaluates each one every 30 min against accumulated activity. Each evaluation includes a "could a generic LLM have produced this?" rebuttal — that's the discriminator between harness-emergence and ordinary LLM output.

loading…

Summary

A cheap model (llama-3.1-8b) describes what each agent has been doing. Refreshes every 30s. Cached 60s server-side.

V2 — primordial agent

Single agent + 14-component cognitive harness (runcor, runcor-substrate, runcor-memory, runcor-data, runcor-integration, runcor-dialectic, runcor-meta, runcor-watchdog, runcor-skills, runcor-drives, runcor-identity, runcor-goals, runcor-temporal, runcor-coherence). Outward actions: firecrawl_scrape, web_search, fetch_chunk, fs_read, fs_write, inbox_read, email_send, git_push, publish_post, terminate.

loading…
ACTIONS (last 20)
control — naive baseline

Single Player call (no Coach, no Judge, no harness). SAME senses + actions as V2 — same model, same budget. The cognitive harness is the only difference. The contrast IS the experiment.

loading…
ACTIONS (last 20)

Transcript

Every cycle event from the live SSE stream, grouped by cycle. Player output rendered as markdown.

loading…