The whole dayThu 19 Nov 2026
AI Compass
WeeklyArchiveAbout

OpenAI details Codex Performance Factory keeping ChatGPT fast

Published on 19 November 2026, outlining cloud Codex state machines and adversarial reviewers that tracked 1,700+ ChatGPT regressions in three months.

Logo: OpenAICover by AI Compass

OpenAI detailed Performance Factory on 19 November 2026, an internal cloud Codex orchestration system combining Markdown task state machines, event subscriptions, a perf-forensics skill and adversarial Codex reviewers that tracked more than 1,700 ChatGPT performance investigations (17 per day) and root-caused over 600 regressions in three months, grading 70% accurate in a 100-case manual audit.

Technical details

Four core system components
Markdown task service, periodic dispatch loop, cloud Codex API and event subscriptions
Three-month Regression Workflow stats
1,700+ investigations (~17/day), 600+ root-caused cases and 70% manual audit accuracy

Release details & context

Self-repairing profiler checks and post-deploy baseline verification

After an engineer reviews and deploys a Codex-authored pull request, Performance Factory wakes a follow-up agent to verify whether ChatGPT latency or CPU telemetry returned to baseline, opening a residual task if recovery is partial. A daily self-repair agent also scans run logs for broken profilers or permission errors across OpenAI’s 30+ internal performance tools.

OpenAI release timeline (56 launches tracked)

  1. Earlier18 Nov 2026
    OpenAI cuts Responses API background tokens up to 40% on GPT-6.2

    OpenAI opens public-beta 2-hour and 8-hour Responses API background windows, cutting Standard token prices by 30% and 40% on GPT-6.2.

  2. Earlier18 Nov 2026
    OpenAI cuts AMD GPU PPA up to 14% and partners on GPT-Synopsys

    OpenAI details up to 14% power, performance and area gains on AMD flagship GPU IP sent to manufacturing and announces GPT-Synopsys with Synopsys.

  3. Earlier18 Nov 2026
    OpenAI reports $2,400 daily median researcher agent spend in RSI study

    OpenAI’s Jagged Frontier report logs $2,400 median daily researcher agent spend, 5.7 agent workdays per day and 77% Safety workweek growth.

  4. Earlier18 Nov 2026
    OpenAI rolls out real-time Live Dictation streaming inside ChatGPT

    OpenAI ships Live Dictation in ChatGPT so spoken words stream into text in real time without post-recording transcription delays.

Explore the full OpenAI dossier or browse all coding agent releases.

Also in the Thursday 19 November edition

Read all 16 launches on one page
  1. 01
  2. 02
  3. 03
  4. 04
  5. 05
  6. 06
  7. 07
  8. 08
  9. 09
  10. 10
  11. 12
  12. 13
  13. 14
  14. 15
  15. 16

Spotted an error? Email aiforsuccess.in+compass@gmail.com or tag @ai_for_success on X

Email Edition · Early Access

Get the 5-minute AI briefing

Daily and Sunday Weekly inbox editions open soon. Join the early-access list.

Zero spam · Privacy

! Please enter a valid email address (for example, you@domain.com).

Morning Edition Alerts

Get a 1-click alert at 11:00 IST

One quiet browser alert when each daily or Sunday Weekly edition goes live between 11:00 and 12:00 IST. No email required. Privacy