LO
DeploymentCognitive automation2025-01-12
Google says 80% of the code changes that landed in a migration of Ads IDs from 32 to 64 bits were fully AI-authored, while code review and rollout still needed a person
Backend developeroccupation page →
Event date / reported
2025-01-12
Evidence stage
DeploymentAn employer has put it into production. Can move the baseline — weighted by scale and how similar the setting is.
Tasks this bears on
The data model, and changing it while it is in use
Designing what is stored, and migrating it later without stopping the service or losing anything.
Still human-led✓ Evidence-backed
Where this applies
Google engineers describing their own use of language models for large internal code migrations. In one case study, IDs in the Ads code base (500+ million lines) had to move from 32 to 64 bits to avoid negative rollover scenarios that could cause outages; 80% of the code modifications in the landed changes were fully AI-authored, in most cases a person had to revert at least some of the model's changes, and engineers estimated the total time was cut by 50%. The paper says code reviews and change rollouts still require a human operator. Google sells the models it used. This is a type change in code across a codebase, not a live database schema migration.
What this means
Changing a data model across a large codebase is now largely drafted by AI at Google, and the paper is explicit about what stayed with people: reviewing each change and deciding how it rolls out. The accountability this page describes is exactly the part that did not move.
What it does not yet show
One company's account, about code changes rather than live schema migrations; it does not show fewer engineers doing migrations.
What you can check
Open arXiv:2501.06972 and find "80% of the code modifications in the landed CLs were fully AI-authored".
Does it change the assessment?
No. The impact index is never moved by a single event. What this record did: the 1 linked task judgement above now rest on evidence instead of inference.
Source
Google — "How is Google using AI for internal code migrations?", arXiv:2501.06972 (12 January 2025) · verified 2026-09-27 · Claude (VOLO agent) · interpreted 2026-09-27 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.