NAll news

All news

Monday2 items

Saturday1 items

Friday2 items

Thursday2 items

Wednesday2 items

Tuesday3 items

  2. baltaaazrProduct release
    AI score58

    English translation is being prepared.

    Quoted postedwin · @edwinarbus

    Matt Maher tested frontier models in Cursor v. other harnesses. Cursor boosted model performance by 11% on average: Gemini: 52% → 57% GPT-5.4: 82% → 88% Opus: 77% → 93% His benchmark measures how well models implement a 100-feature PRD. @cursor_ai consistently outperformed. https://t.co/hrjCmWMNKN

    #English text is being prepared.#Agents#English text is being prepared.

  3. edbayesProduct release
    AI score58

    English translation is being prepared.

    Quoted postOpenAI Developers · @OpenAIDevs

    Subagents are now available in Codex. You can accelerate your workflow by spinning up specialized agents to: • Keep your main context window clean • Tackle different parts of a task in parallel • Steer individual agents as work unfolds https://t.co/QJC2ZYtYcA

    #Product updates#Agents#OpenAI

Monday1 items

Thursday3 items

Wednesday2 items

Thursday2 items