Use case registry

Security, Science & Hardware

Debug low-level cryptography code

Cryptography engineer Filippo Valsorda's write-up on Claude Code debugging low-level crypto.

What they did

Filippo Valsorda ran Claude Code (Opus 4.1, no system prompt) on his new Go ML-DSA implementation. His prompt named the test command and code directory, described the failing symptom, and asked it to think hard. It read the code and traced the bug. It also tested a hypothesis with a small test of its own. He then repeated this on two earlier signing bugs, using a fresh session for each.

How it went

It found all three bugs in one shot without help. The Verify bug took minutes: high bits were taken twice. Its proposed fixes were mediocre, so Valsorda threw them away and rewrote them himself.

Worth knowing

Use well-scoped failing tests, start a fresh session for each independent bug, and treat the agent's output as a pointer to the bug, not a fix to merge.

Labels

ScopeBusinessIt read the code and traced the bug.

For whomIndividualFilippo Valsorda ran Claude Code (Opus 4.1, no system prompt) on his new Go ML-DSA implementation.

What the agent doesWriting codeIt read the code and traced the bug.

How autonomous the agent isPrepares, a person actsIts proposed fixes were mediocre, so Valsorda threw them away and rewrote them himself.

Agent or ordinary appAgent productIt read the code and traced the bug. It also tested a hypothesis with a small test of its own.

Already a company's productUnclear

What kind of materialunverifiedFirst-hand accountCryptography engineer Filippo Valsorda's write-up on Claude Code debugging low-level crypto.

The “Material” label failed its quality check and is not used for selection.

Details

Agents: Claude Code
Source: Hacker News
Source date: Nov 1, 2025
Accounts: 1
In registry since: Oct 12, 2026

Original source ↗