FR
live
tag

#code-review

An AI code review bot rejects a security fix by inventing a CVE that does not exist

On October 29, 2026, Docker recounted how a code review bot running locally through Ollama refused a routine PostgreSQL version bump by citing a CVE that was never issued. The lesson applies to any team wiring an AI agent into its pipeline: an agent’s output is untrusted input, to be labeled and verified as such.

Anthropic’s scanner finds 29,000 candidate bugs in open source, only 516 patched

On 11 October 2026, the disclosure dashboard behind Anthropic’s free open-source scanner showed its models surfaced more than 29,000 candidate vulnerabilities in six months, with just 516 patched upstream. If you maintain a critical project, the new “fast-track” now ships raw, unvalidated findings straight to you: sorting them is your job.

GitHub stacked pull requests go GA with 9% more merged code

GitHub announced general availability for stacked pull requests, which split a large change into small, independently reviewed pull requests that merge together at the end. If your branches keep blocking each other, GitHub’s numbers — 9% more merged code and 5% faster time-to-merge — justify adopting them now.

systemd 262-rc2 adds an AI canary to catch unreviewed LLM code

On September 8, 2026, systemd 262-rc2 shipped an AI canary in its AGENTS.md file: a trap instruction that forces AI coding agents to mark the patches they produce, and whose manual removal proves a human actually reviewed the code. A simple, copyable mechanism for any project receiving AI-generated contributions.

Type at least two characters.

↑ ↓ navigate ↵ open esc dismiss