Just keep auditing Post
Letting Claude audit and fix the Rust symbolic execution engine eight times over two months and no sign of convergence.
Automation
Are we there yet? Ten weeks of Rust Symex Post
Ten weeks of letting Ralph grind on the Rust symbolic execution engine – 2,593 iterations, six moonshots, runaway memories, and endless audits.
Perfect is the enemy of good Post
Chasing a bug-free Forge with Claude – 209 issues, a fuzzer, two AI code audits, and learning when to stop.
Solvent Streets Post
Building a tool with Claude to measure my city’s pavement and forecast its maintenance cost — a look at the fiscal toll of car-dependent design.
Forge end-to-end testing Post
Building out Forge’s end-to-end test suite with Claude, beads, and a sandboxed feedback loop.
From Bash Loops to a Ralph FSM Post
Evolving a Ralph-style Claude loop from a one-shot bash script into a generic Go tool driven by a finite state machine and reusable Go-CLI design scaffolding.
Towards a Rust Symbolic Execution Engine Post
After months of iteration with Claude, a Rust port of Angr’s symbolic execution engine that matches or beats Python on most CTF benchmarks – up to 12.7x on the largest.
Hand tools versus Power tools Post
What barrel-making teaches us about AI and the future of software development.
Can AI Test All Code Like SQLite? Post
SQLite has 590x more test code than library code. Can AI help us achieve that level of testing for all software?
Forge, meet Claude, part 4 Post
Final progress on Forge bug fixes and thoughts on the challenge of upstreaming AI-assisted contributions.