Auto-Arch Tournament vs Modo

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.

Modo is an open-source AI IDE built on the Void editor (a VS Code fork) that flips the script on how AI coding tools work. Instead of jumping straight to code generation, Modo forces a spec-first workflow: describe what you want, and the agent converts your prompt into structured requirements docs, design docs, and task breakdowns stored in a persistent `.modo/specs/` directory before writing a single line of code. The approach draws from the "vibe coding is bad actually" school of thought. Modo's steering files and agent hooks let developers set coding conventions, stack preferences, and project constraints that persist across sessions. Autopilot mode chains spec generation through implementation, while parallel chat lets you run multiple agent conversations simultaneously against the same codebase. Built by a solo developer and posted to Hacker News as a Show HN, Modo positions itself against Cursor, Windsurf, and Kiro. The bet: slowing down agents with structured planning up front produces fewer hallucinated architectures and rewrites. It's early — rough edges abound — but the spec-driven philosophy is increasingly mainstream as larger teams adopt AI coding tools.