Files
hermes-brain/ideas/self-driving-lisp-machine.org
Hermes 2578bfee61 Architecture reframe: rename triad/Stoa/Logos/Agora → Passepartout
- Renamed ideas/stoa/ → ideas/passepartout/, all stage files prefixed passepartout-
- Renamed triad-index/overview/systemic-effects → passepartout-* under passepartout/
- Renamed ideas/agora/ → ideas/passepartout-social-protocol/, stripped agora- prefixes
- Merged overview and environment pages into architecture; deleted 3 redundant files
- Renamed growth-strategy → enterprise-growth-strategy
- Renamed alternative-growth-social-first → social-growth-strategy
- Removed all Greek names: Stoa, Logos, Agora as product names
- Updated 50+ files of cross-references to new naming
- Kept org-id UUIDs intact throughout
2026-05-24 18:02:36 +00:00

2.1 KiB

The Self-Driving Lisp Machine

A Tenstorrent P150 (~72 RISC-V Tensix cores) running Passepartout: 72 RISC-V cores running Lisp microcode, one core dedicated to ACL2, one to Screamer, the rest to gate verification and fact store operations.

The self-driving threshold: the system can synthesize and load its own FPGA microcode or Tensix dispatch programs from within the running Lisp image. The system profiles its own gate verification latency, proposes a new microcoded instruction for the hot path, compiles RISC-V assembly from ACL2-verified specifications, loads it via PCIe DMA from within SBCL, benchmarks it — and rolls back if slower.

Every subdomain involved is software — the most codifiable domain. RISC-V ISA, SBCL internals, ACL2 metafunctions, CIC type theory, compiler optimization — all can flip to symbolic sufficiency within days to weeks of ingestion.

Timeline: ~6,000 lines of new code (microcode, PCIe DMA, Tensix management, benchmark harness). ~60 cycles at current velocity. 2-4 weeks. Total from today: 6-10 weeks. See time estimates for the velocity model behind these numbers.

The Tenstorrent approach is dramatically simpler than FPGA because the microcode is RISC-V assembly (software), not FPGA bitstream (hardware with minutes-per-iteration synthesis). The Lisp Machine security model — unified memory, tagged architecture, no MMU — applies directly because the Tensix cores share the same address space. Verification appliance economics apply: a certified Lisp Machine at scale replaces compliance hardware. See why Lisp is economically viable now and upgrade lifecycle for the economic and deployment foundations.