Topic
Using language models and agents to review code, including cross-family or adversarial review where one provider's model reviews another's output.
Tessl Code Review, free during beta, keeps review criteria as versioned files the team owns instead of logic sealed inside a vendor product. Someone still has to write the criteria.
Reality
A developer's OWASP Benchmark test showed the model's failure was optimism, not ignorance. His fix flips the default on unknown functions, which moves the error rather than removing it.
Reality
A New Stack column argues AI-generated diffs have made careful review impossible. The automatable half of the job is bug-catching; the half nobody has staffed is knowledge transfer.
Reality
Anthropic says the model now verifies by default, so the double-check lines can go. The four-hundred-line diff behind the green check still has to be read by someone.
Reality
A dev.to walkthrough argues code review pipelines should merge lexical and vector candidates by rank, rerank a bounded pool, and withhold findings whose cited policy passage is stale or unreadable.
Reality
A vendor writeup argues cross-family AI review fails on inputs, not model choice: the diff shows what changed, the agent session shows whether it was asked for. The evidence is one anecdote.
Reality