AI SAFETY TWITTER UPDATES

← Front page

Anthropic scales code merges to 30k/day, prioritizing intent interpretation

2 people · 2 posts · first post · latest

Nathan Calvin noted that Anthropic is shifting from line-by-line code review to focusing on the intent of changes due to scaling. The company reported increasing daily code merges from 2,500 in May to over 30,000 in September, placing significant reliance on accurately interpreting the intent of Claude's complex outputs.

All posts · 1, most important first

  1. @_nathancalvin policy ·
    Not super surprising, but still very striking. Anthropic says they now focus on reviewing the "intent" of code changes rather than actually reading code. Anthropic is placing a tremendous amount of load bearing trust in interpreting Claude's intentions correctly
    image
    @anthropicai: New on our Engineering blog: Creating in-house source control. In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000 per day. As a result, we became bottlenecked by developer infrastructure built for human (rather than agent) scale. Here, we share how we built a new version control system—and fully migrated our monorepo from git—in five months: anthropic.com/engineering/re… open on X
    6 likes · 0 reposts

Reposted by @miles_brundage.