OPENAI CUTS CODEX CONTEXT WINDOW BY 100K TOKENS
■ AI-SUMMARIZED FROM 5 SOURCES ▸ TIMELINE
OpenAI has reduced the maximum context window for its Codex model from 372,000 to 272,000 tokens, according to changes merged in the model's repository. The reduction represents a 27% decrease in the amount of code and context the model can process simultaneously.
■ SOURCES
► Engadget► Hacker News► Hacker News► Bleeping Computer► Techmeme■ SUMMARY WRITTEN BY AI FROM THE LINKS ABOVE
■ MORE FROM THE DEV DESK
Spotify Engineering has published findings on Portal, a tool that dramatically reduces token consumption when using Claude Code. The optimization reportedly cuts token usage by 90%, suggesting significant cost and efficiency gains for developers.
Audacity 4 is now available with a complete redesign that modernizes the free audio editing platform. The update delivers on long-promised improvements to transform the interface from functional but clunky to streamlined and powerful.
K2 Horizon introduces a new approach to frontier performance with radically open architecture. The platform targets developers seeking transparency and extensibility in high-performance computing.
A significant shift is reshaping frontend development practices, according to developer Nolan Lawson. The change has sparked intense discussion in the developer community with over 128 comments on Hacker News.