Anthropic AI researcher Andrej Karpathy suggested long voice input, rather than meticulously written prompts, as a way to use generative AI effectively. On July 24, Business Insider reported that Karpathy said he often uses a method in which he turns on voice mode and speaks freely for about 10 minutes about project-related thoughts. In a post on X on July 22, Karpathy described the approach as a "stream of consciousness" that is "completely messy and anything goes." He said that if users deliver fragmented ideas and concerns all at once, a large language model can organise them more systematically. Karpathy said the method is also simple in practice; he starts by telling the AI his thoughts may be mixed up and then speaks at length about the project, having the AI summarise and structure the main points. Some X users responded sceptically, saying a long voice monologue does not always produce better results. The remarks come as big tech companies step up competition over voice-based AI features; OpenAI unveiled a new model, GPT-Live, and Anthropic on July 24 also announced a voice function update.