At a Y Combinator event, Boris Cherny, the mind behind Anthropic's Claude Code, advised against drowning AI chatbots in super-detailed instructions, stating that giving too much direction can hold back what advanced models can do. Instead, he recommended setting clear goals and basic rules without writing an essay. Cherny noted that AI is moving fast, as what worked six months ago might already be old news. He backed the idea of "lazy prompting," credited to Google Brain co-founder Andrew Ng, which means keeping instructions short and focused. Cherny also shared that his team keeps finding new abilities in their models, indicating there is still a lot more under the hood than realized.