Expired70% confidenceFactTime unknown
Codex Max's Compaction technology can automatically compress history, and OpenAI claims this enables the model to maintain coherence across millions of tokens, sustaining continuous work for more than 24 hours in internal testing.
1
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
GPT-5.1 Pro Deep Dive: The Smartest AI Trapped in the Worst Interface
bilibili安得广厦千万间678
Related Entities
Related Claims
UnverifiedIn actual testing, Codex completed a search result sorting bug fix task in 2 minutes and 18 seconds.65% similarUnverifiedThe UP host ultimately used OpenAI's Codex desktop version to handle coding tasks, with a single task processing time of approximately 21 minutes.65% similarUnverifiedCodex ran continuously for more than 20 hours on the migration task, autonomously completing cycles of understanding the project, building, identifying issues, and modifying code.64% similarUnverifiedA trained neural network surrogate model can produce approximate results within milliseconds, compressing design iterations that would otherwise take years down to weeks or even days.64% similarUnverifiedCodex generated more than 2,000 lines of code in 34 minutes.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/12480API
curl https://kongchang.com/api/v1/knowledge/claims/12480MCP
get_claim(id=12480)