An Anthropic engineer has argued that the best way to use Claude is not to type prompts by hand, but to build a self-prompting system in which the setup itself generates and runs prompts — a view drawing attention among developers. The idea traces back to comments from Boris Cherny, known as the creator of Claude Code, who is widely quoted as saying, in effect, "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops."
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.