Sourcegraph CEO: AI-generated code is decaying large codebases at scale
AI Engineer · youtube · 2026-10-05
At AI Engineer World's Fair 2026, Sourcegraph CEO Dan Adler argued that owners of huge, decades-old codebases (banks, cars, airlines) face accelerating decay — duplicated code, drifting standards, brittle dependencies, and new vulnerabilities — as coding agents produce a tidal wave of AI-generated code.
Key points:
- Agents understand code by searching, but "you can't grep what you can't see": at enterprise scale, context and code visibility — not model quality — are the bottleneck.
- Adler argues large-scale code visibility is infrastructure, and introduced Sourcegraph's Agentic Batch Changes, which makes and audits changes across thousands of repos from a single prompt.
- Includes a case study with Mercari and a call to dev tools builders.
More from coding & agent
- TanStack AI adds experimental text-to-GLB 3D model and prompt-to-motion animation generation — bennash · 2026-11-20
- Dev builds typing survival game with troops and skill trees in ~24 hours using agents and kaigen3d — hullabaloo22 · 2026-11-20
- Harmonic's Aristotle writes proven-correct fusion plasma controllers in C and Verilog in 4 hours — satnam6502 · 2026-11-20
- R3 Code: A Native Rust Mac Client That Runs All Your Coding Agents — jasonkneen · 2026-11-20
- zlib: 2.4K-star open-source CLI turns Z-Library into a skill for AI agents — udmrzn · 2026-11-20
- Andriy Burkov's True Positive Weekly #186: what to know when agents do the work — burkov · 2026-11-20