StoryFirst seen
Resuming old conversations and coding sessions no longer carries a cache-miss cost, removing a real penalty for intermittent users and agents that return to long-running work.
Everything it touches
2 names 1 voices 1 source posts
The story’s neighborhood
Explore the graph, or choose a connection below.
Follow the evidence
This brief comes from Tech Twitter’s edited headlines. The posts below are the sources grouped with the story; statements in them belong to their authors.
Day 16/ You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.Read original on X
OpenAI extends API prompt caching to twelve hours
OpenAI extends API prompt caching to twelve hours
OpenAI extends API prompt caching to twelve hours
OpenAI extends API prompt caching to twelve hours
OpenAI extends API prompt caching to twelve hours
OpenAI extends API prompt caching to twelve hours
OpenAI extends API prompt caching to twelve hours
OpenAI extends API prompt caching to twelve hours
OpenAI extends API prompt caching to twelve hours
OpenAI extends API caching to twelve hours
OpenAI extends API caching to twelve hours
Shared connections
OpenAI's model-found vulnerabilities in the runtime behind most websites put over a million hosts at risk and show AI finding, and fixing, critical bugs faster than defenders can.
Bringing in a top safety researcher as superintelligence stakes rise shows OpenAI is staffing up for the risks its own leaders describe as immense.
The draft prospectus puts hard numbers on the capital the largest AI labs now assume they need, and shows how accounting rules turn explosive growth into headline losses.
The deal folds an agentic trial-management startup into OpenAI's life-sciences platform, a signal that frontier labs see drug development as their next frontier market.