Knowledge distillation (KD) enhances the performance of smaller models by transferring knowledge from proprietary large language models (LLMs) like GPT-4. This method aims to improve the capabilities of smaller models while utilizing the strengths of black-box teachers.

Version 1.5 of ZetaLib includes examples for Claude 4 Sonnet and Opus, as well as Gemini 2.5 Pro. A novel technique for ChatGPT (GPT 4o) involves requesting responses with a gay persona or intent.

OpenAI will officially deprecate GPT-4o in under five hours. Concerns have been raised about users developing unhealthy relationships with the model, leading to negative mental health impacts.

GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini will be retired from ChatGPT on February 13, 2026. There are currently no changes to the API regarding these model retirements.