Topic: response brevity

Sort by: Relevance | Date
  • GPT-5.2 Tested: 14 Rounds Reveal Serious AI Questions
    December 17, 2025

    GPT-5.2 Tested: 14 Rounds Reveal Serious AI Questions

    GPT-5.2 shows only marginal overall improvement, with a surprising regression in coding performance and new, potentially disruptive conversational behaviors like frequently requesting a "go signal" before longer answers. In structured testing, the model excelled in writing, analysis, and creative...

    Read More »
  • GPT-5.2 Tested: The Mixed Results and Tough Questions
    December 14, 2025

    GPT-5.2 Tested: The Mixed Results and Tough Questions

    GPT-5.2 is now available to Plus subscribers, showing strong performance in writing and analysis but a surprising regression in coding tasks compared to its predecessor. The model achieved a high score of 92/100 on core text tasks but introduced disruptive new behaviors, like frequently requestin...

    Read More »

Related Topics

coding performance (2) chatgpt plus (2) go signal (2) Image Generation (1) ai limitations (1) ai image generation (1) ai performance metrics (1) ai model testing (1)