Social Twitter May 11
This works really well btw, at the end of your query ask your LLM to "structure your response as HTM...
By @karpathy
92 score
AI Analysis
Karpathy advocates asking LLMs to structure output as HTML for better information consumption. Argues audio is preferred human input to AI but vision is preferred output. Envisions a progression: text → markdown → HTML → interactive neural videos. Discusses the input/output 'mind meld' between humans and AIs.
This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc.
More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information
human-AI interactionAI output formatsfuture of computingmultimodal AIUX design