Auto-Arch Tournament vs LaReview

Auto-Arch Tournament is an autonomous research system where an AI agent iteratively proposes, implements, and validates microarchitectural improvements to a RISC-V CPU. Starting from a standard 5-stage pipeline, the loop runs hypotheses in parallel, each going through formal verification (53 symbolic checks), cycle-accurate simulation, multi-seed FPGA place-and-route, and CoreMark CRC validation. Only hypotheses that beat the current champion get merged; everything else gets discarded. Starting from 301 iterations/second, the system hit 577 iter/s (+92%) across 73 attempts in 9.8 hours — producing a design 26% faster and 40% smaller in LUTs than the baseline. The insight the author drives home is that the real innovation isn't the AI agent — it's the verifier. The orchestrator is hardcoded to prevent agents from manipulating their own evaluation gates, a simple but critical design constraint that turns a creative process into a trustworthy one. Without a rigorous verification harness, agent-driven optimization becomes a confidence trick. This is early but fascinating proof that AI-driven hardware design loops can produce commercially meaningful gains. The repo uses Claude Code or Codex as the coding agent, SystemVerilog for the RTL, and standard open-source EDA tooling (Yosys, nextpnr, Verilator). It's a compelling template for anyone building agentic optimization loops where correctness matters.

LaReview is a code review workbench built on a local-first, privacy-preserving architecture. It pulls PRs directly via the gh or glab CLI — your code never touches LaReview's servers. Once a diff is local, it converts it into a structured review plan with architectural diagrams, then chains your existing AI coding agent (Claude Code, OpenCode, Codex, etc.) to perform the actual analysis. LaReview acts as the orchestration and memory layer, not the LLM. The tool learns from reviewer feedback over time: when suggestions are rejected, that signal trains a local preference model that shapes future reviews toward your team's actual standards. The local-first approach means teams with strict IP or compliance requirements — financial services, defense contractors, regulated healthcare — can use AI-assisted code review without data leaving their environment. Launching on Product Hunt today at #5 with 85 upvotes, LaReview addresses a specific pain point for security-conscious engineering teams who've avoided tools like CodeRabbit or GitHub Copilot Code Review precisely because of data residency concerns. The chain-your-own-agent model also means teams aren't locked into LaReview's model choices as the AI landscape evolves — a meaningful advantage given how fast model quality is shifting.