Videos

IDEs are no longer primarily for writing code; they are becoming tools for reading, reviewing, and verifying code...

Nick Nisi built a fruit fly brain simulation that reviews JavaScript pull requests, using a connectome of 176,000...

Cross-model review—building with one frontier model and reviewing with another—is the most effective way to catch...

A one-line change to a data model can break multiple downstream repos (web, mobile, CLI), and most developers merge...

Anthropic has scaled from merging roughly 2,500 code changes per day in May to about 30,000 per day by making...

AI-generated code is 10xing commit rates, but the CI and review queues built for human speed are now the bottleneck,...

Structured quality gates—codified as rules, skills, and planning templates—can be operationalized across the AI...

The central tension in AI-assisted development is that generation is cheap but evaluation is expensive, and the...

Whether you read AI-generated code is a context call, not a rule. Production code at Sentry gets read line by line....

Exa's semantic search is designed to replace the ten blue links of Google with context-rich highlights that are...

Agent-generated code passes tests far more often than it deserves to merge: SWE-bench's 'good enough to merge'...

A quarter of pull requests at large companies are now completely or largely AI-generated, up from under 1% a year...

The talk argues that agents have a measurement problem because token spend is not clearly tied to outcomes, making...

AMP has killed mandatory code review for its 20-person team, relying instead on high-trust, high-ownership engineers...

The main flaw with AI coding agents is that they produce code that is syntactically correct but violates business...

Uber's UReview system reduced code review costs by 60% and improved accuracy by 70% through an observability...