Research-Stack/6-Documentation/chat-log-dumps/README.md
Brandon Schneider 0cf775c80e collapse: prover orchestration layers, FAMM verilator harness, swarm topological prober, spec sheets, virtual FPGA system tests, merge conflict resolution
- Prover-Integrated Orchestration Layers (L0-L3): Goedel-Prover-V2 watchdog, BFS-Prover-V2 swarm consensus, bf4prover topology adaptation
- FAMM Verilator benchmark: uniform vs preshaped delay comparison (4.4x speedup)
- Swarm topological device prober: 11 agents probing traces, caps, delays, errors, vias, PDN
- Spec sheet puller: 10 components with key params and topological relevance
- Virtual FPGA system tests: 6/6 passed, 134K ops/s throughput
- Fixed merge conflicts in AI-Newton test_experiment.ipynb
2026-05-06 23:42:01 -05:00

1 KiB

Chat Log Dumps

This directory is the parse-friendly index layer for full conversation dumps.

It does not duplicate every raw chat export. Instead, it records where the full logs live, what format they use, how large they are, and which broad research lanes they appear to touch. The local TiddlyWiki can link to this section without embedding huge transcripts into .tid files.

Files

  • build_manifest.py scans known conversation/export pools.
  • manifest.jsonl is generated and contains one JSON object per source file.
  • summary.md is generated and gives a small human-readable inventory.

Source Pools

  • 5-Applications/audit/exploit-audit/sessions/
  • shared-data/data/germane/research/
  • shared-data/data/ingested/chatgpt/
  • shared-data/data/ingested/llm_research/
  • 6-Documentation/archive/sessions/chatgpt-logs/

Refresh

python3 6-Documentation/chat-log-dumps/build_manifest.py

Generated rows are intentionally conservative. A source can be large, messy, or duplicated; the manifest should still keep it discoverable.