Understand this story
In a talk at aiDotEngineer, Addy Osmani said Anthropic's daily merge volume rose from about 2,500 in May to roughly 30,000. The approach he described is that Claude performs the first round of review, but it must attach evidence such as end-to-end, browser, lint, test, screenshot, or video artifacts; humans review the evidence package rather than reading every diff line by line. The process also includes using hooks to watch edits and diffs, and writing team conventions into CLAUDE.md or agents.md. Osmani believes Claude Opus 5.5 is already sufficient, and that the next wave of gains lies in verification practices. The same report also mentioned that on the CircleCI side about 30% of merge attempts still fail, and that SonarSource recommends independent verification and guardrail-style constraints at each stage of agents, CI, and maintenance.
AI-generated from public reports
Developments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 1
Shao Meng
Anthropic's daily merge volume rises to about 30,000: relying on verifiable evidence rather than reading diffs line by line
In a talk at aiDotEngineer, Addy Osmani said Anthropic's daily merge volume rose from about 2,500 in May to about 30,000; the approach is that Claude performs the first round of review, but must attach evidence such as end-to-end, browser, lint, test, screenshot, or video evidence, and humans review the evidence package rather than reading through every diff line by line. The process also includes using hooks to watch edits and diffs, writing team conventions into CLAUDE.md or agents.md, and holding that Claude Opus 5.5 is already sufficient, with the next wave of gains lying in verification practices. CircleCI noted that about 30% of merge attempts still fail, and SonarSource suggested independent verification and guardrail-style constraints at each stage of agent, CI, and maintenance.