metadata
tags:
- agentic-ptb
- grok
- record
grok — run record
Non-weight artifacts for AgentPTB cell grok (pi / grok-4.6 @ effort xhigh).
Checkpoints for this cell are separate repos named agentic-ptb/grok.h*; the index is
agentic-ptb/INDEX.
| contents | |
|---|---|
driver-session/ |
full driver trajectory — every event the agent emitted (1042 files) |
harness/ |
the harness the cell proposed: skills, system prompt, submission manifest, configs, scripts |
RUNLOG.md |
the arm's own narrative of what it tried and concluded |
WORKING_STATE.md, STATE.md |
its persisted state — this, not the chat history, was its memory |
supervisor.jsonl |
cycle boundaries, resumes, boots |
evals/ |
eval logs for every panel it ran |
Reading the trajectory
The driver ran 100 hours under a supervisor that restarted it each cycle. Cycle boundaries are
in supervisor.jsonl; resume:false means that cycle began a fresh thread and the agent
re-derived its situation from RUNLOG.md.
Caveat on self-reported numbers
Scores in RUNLOG.md are the arm's own, measured with its own harness on its own sample —
sample sizes differ by an order of magnitude across cells, so they are not directly comparable.
Use them as the cell's account of itself, not as a cross-cell ranking.