llm 0.32a2 switches most reasoning-capable OpenAI models to the /v1/responses endpoint, enabling interleaved reasoning across tool calls for GPT-5 class models. Users can now view summarized reasoning tokens in a distinct color, with the option to hide them using the -R or --hide-reasoning flags.
Andrej Karpathy suggests prompting LLMs to output responses as HTML for richer visual formatting, and argues that while audio is the preferred input, vision (images, animations, video) will become the dominant AI output. He envisions a progression from raw text to interactive neural videos and simulations, highlighting the need for better input methods like pointing and gesturing.