Finding Miscompiles for Fun, Not Profit - by Justin Lebar
newsletter.semianalysis.com · 1,725 words · saved by 1 readers
Or: You don’t need access to Claude Mythos to spend $10,000 in an afternoon.
Finding Miscompiles for Fun, Not Profit Or: You don’t need access to Claude Mythos to spend $10,000 in an afternoon. Justin Lebar May 28, 2026 ∙ Paid 214 8 Share Update June 1: The day after we published, Anthropic released Opus 4.8 and “ultracode” mode in Claude Code. Our preliminary experiments indicate that together these are significantly better at filtering out low-severity bugs, and that the cost per medium-to-high severity bug found is maybe 1/5 (with very large error bars) that of the workflow described in this article. I’ve worked on compilers for ML for the last decade across Google,
saved by
related reading
- When AI Writes the World's Software, Who Verifies It? — Leonardo de Mouraleodemoura.github.io
- A friendly introduction to machine learning compilers and optimizershuyenchip.com
- Astra for Coding: Why Are We Doing This Again?lucumr.pocoo.org
- claude code is not making your product betterethanding.substack.com
- Earn $200K by fuzzing for a weekend: Part 1 | secret clubsecret.club
- Claude Is Not a Compilerblog.exe.dev
- What it feels like to work with Mythos - by Ethan Mollickoneusefulthing.org
- Building a C compiler with a team of parallel Claudes \ Anthropicanthropic.com
- There's no reason for software to be slow anymoredanluu.com
- ⭐️ Fast LLM Inference From Scratchandrewkchan.dev
- How Compiler Explorer Works in 2025 — Matt Godbolt’s blogxania.org
- My Claude Code Psychosissubstack.com