Files
hermes-brain/ideas/self-driving-lisp-machine.org
Hermes 3e32ea9959 Promote entire passepartout-economics/ to ideas/ root
All 31 files from ideas/passepartout-economics/ promoted to ideas/ root.
- Subfolder's passepartout-economics.org (42-line index) renamed to
  triad-index.org to avoid collision with root-level full doc
- index.org removed (redundant — triad-index.org replaces it)
- Root-level passepartout-economics.org: stripped file:passepartout-economics/
  prefix from all cross-references (now simple file:foo.org links)
- compliance-framework-mapping.org: same prefix cleanup
- All internal file: links within the economics docs already used simple
  names (no prefix) — they resolve correctly from ideas/ root
2026-05-23 06:09:08 +00:00

2.0 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.