Intel / video

AI-Generated Code Is Already Competing With Human Code — Daksh Gupta, Greptile

Source: youtube.com
Author: AI Engineer
Date: Published Sep 25, 2026

Context

Greptile, a code-review service, reports that pull requests it identified as -written (using signals such as author fields, co-author footers and branch prefixes) landed in the same range as human-written ones on the quality measures discussed in its conference presentation. Those measures include how often changes were reverted, the severity of issues Greptile flagged and the review rounds needed to reach a mergeable change.

The reported similarity does not mean the mistakes were identical: the presentation describes different failure patterns among tools, such as SQL injection, authentication bypass and inefficient database queries. Its useful implication is that reviewing generated code requires to the kinds of defects a tool produces. These are company-reported comparisons within the pull requests Greptile reviewed, rather than proof of universal equivalence.

Key takeaways · AI-distilled

Greptile co-founder Daksh Gupta says more than a quarter of the pull requests Greptile reviewed in April showed signs of being written largely or entirely by AI agents, up from under 1% a year earlier. The sample is over a million PRs a month.
Gupta compared agent and human PRs on four measures: revert rate, revert rate by PR size, severity of flagged issues and review rounds needed to reach a mergeable PR. Agent code landed in the same range on all four, and humans were more likely to introduce P0 bugs.
Greptile identifies agent-written PRs from author fields, co-author footers and branch prefixes, according to the talk's methodology segment.
Gupta argues manual review cannot keep up: the median Greptile user makes fewer than 50 commits a month, the 99th percentile close to 1,000. He proposes validating whether a change breaks the user contract, makes a future break likelier, or misses the author's intent.

Terms in this piece · Glossary

AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
attention — The mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.

Read the source www.youtube.com