---
type: "post"
id: "maintaining-software-with-the-gpt-6-family-2a875d"
slug: "maintaining-software-with-the-gpt-6-family-2a875d"
title: "Maintaining software with the GPT-6 family"
description: "OpenAI’s Core Experimentation team published a case study on using GPT-6-family coding agents to maintain internal software: removing unused code, auditing stale experimentation configuration, and reducing CI load."
retrieval_nugget: "OpenAI’s Core Experimentation team published a case study on using GPT-6-family coding agents to maintain internal software: removing unused code, auditing stale experimentation configuration, and reducing CI load."
published_at: "2026-10-26"
updated_at: "2026-10-26"
record_date: "2026-10-26"
date_kind: "published_at"
topics: ["coding-agents","codex"]
entities: ["OpenAI","Core Experimentation","GPT-6 Astra","GPT-6.1 Sol","Codex","Statsig"]
related_patterns: ["verification-bandwidth-is-the-scarce-resource","harness-architecture-outlives-model-choice","goal-scoped-loops-replace-manual-continuation"]
novelty_label: "new_angle"
what_changed: "OpenAI describes its own use of GPT-6 models to identify and clean up maintenance work, complementing Uber’s flag-removal system with a broader internal software-maintenance perspective."
prior_refs: ["memory:69daf68f-dd7e-8b32-acf4-cb34801d43a7"]
source_url: "https://developers.openai.com/blog/maintaining-software-with-the-gpt-6-family"
source_urls: ["https://developers.openai.com/blog/maintaining-software-with-the-gpt-6-family"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:maintaining-software-with-the-gpt-6-family-2a875d"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/maintaining-software-with-the-gpt-6-family-2a875d/","markdown":"https://newruntime.com/posts/maintaining-software-with-the-gpt-6-family-2a875d.md","json":"https://newruntime.com/posts/maintaining-software-with-the-gpt-6-family-2a875d.json"}
---

# Maintaining software with the GPT-6 family

## Retrieval answer

OpenAI’s Core Experimentation team published a case study on using GPT-6-family coding agents to maintain internal software: removing unused code, auditing stale experimentation configuration, and reducing CI load.

OpenAI’s Core Experimentation team published a case study on using GPT-6-family coding agents to maintain internal software: removing unused code, auditing stale experimentation configuration, and reducing CI load. The team says GPT-6 Astra gathered evidence from past pull requests, Slack, project trackers, Statsig, and production profiling before preparing changes for review.

Five engineers ran cleanup work part-time over two weeks and merged more than 1,400 pull requests, deleting over 800,000 lines of code. OpenAI reports that one service image fell from 3.31 GB to 1.72 GB, while another cleanup removed about 400 visual snapshot variants. For stale experiments, the agent produced reports rather than changing live services; one subsequently reviewed removal was associated with roughly 0.42% CPU savings on a service.

In one 6,000-file, roughly one-million-line audit, OpenAI reports 142 findings for GPT-6 Astra Ultra at $109.06 and 131 for GPT-6.1 Sol Ultra at $15.12. It also says approximately 30 CI optimization pull requests reduced median CI time from about 10 to 4.5 minutes. The post is an internal case study and does not establish that these results, costs, or safety outcomes will reproduce in other repositories.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Coding Agents](https://newruntime.com/topics/coding-agents.md): Explore the coding-agents topic hub.
- topic hub: [Codex](https://newruntime.com/topics/codex.md): Explore the codex topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)