Study finds async AI coding agents drive far bigger output gains than autocomplete
NathanpmYoung · x · 2026-07-25
A figure from a study on AI coding tools compares productivity gains across three generations of tooling:
- Autocomplete (e.g. GitHub Copilot at launch)
- Sync agents (e.g. Claude Code run locally)
- Async agents (e.g. OpenAI Codex run remotely)
The chart shows the biggest gains from asynchronous agents, with roughly:
- 17.3× more lines of code
- 3.9× more files touched
- 2.8× more commits
- 2.5× more pull requests
- 1.5× more repos touched
- 1.3× more releases
The takeaway is that more agentic workflows appear to correlate with much larger throughput changes than classic autocomplete.
More from coding & agent
- GPT-5.6 Agents Collaborate for 40 Hours to Boost Kimi K3-like Model Inference to 406 tok/s — nicodotdev · 2026-07-25
- Stardock is using AiClairvoyance to let project-manager AIs hire AI staff — draginol · 2026-07-25
- tldraw offline tops 13,150 downloads before adding Pi agent skills — max__drake · 2026-07-25
- Grok Build’s new workflow feature makes 20-agent code review practical — tylerbruno05 · 2026-07-25
- ComfyUI tutorial shows how to guide motion in LTX 2.3 with public nodes — nghtdrp · 2026-07-25
- Builder is making an AI receptionist for small clinics to handle calls and bookings — Icy_Current9287 · 2026-07-25