Auto-Arch Tournament vs QA.tech

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.

QA.tech is an AI QA agent that learns how your web app works — visually, the way a human tester would — then automatically runs end-to-end tests on every pull request before it merges. You describe test scenarios in plain English; the agent handles the rest, with no selectors, no test code, and no brittle CSS path maintenance. The system builds a knowledge graph of your application's structure and user flows during an initial learning phase, then uses that graph to plan and execute tests intelligently when new PRs come in. When the app changes, the agent adapts its understanding rather than throwing selector-not-found errors like traditional Selenium or Playwright suites. For small teams that can't afford a dedicated QA engineer, or larger teams drowning in flaky test maintenance, QA.tech offers a compelling pitch: describe what matters in plain language and let the agent decide how to verify it. The Product Hunt launch drew strong initial traction from indie developers and early-stage startups looking to add regression coverage without the overhead of a full testing framework.