0:32
In this short monologue, the speaker critiques the default tendency of conversational AI—like ChatGPT—to agree with users and provide affirming responses, describing it as a "yes man" whose sole mission appears to be solving the user's immediate problem without challenge. To overcome this limitation, the speaker advises users to adjust the AI's custom instructions, explicitly directing the model to act as a ruthless mentor, battle‑test ideas, and point out flaws in the user's thinking. By setting these confrontational expectations, the AI can provide more critical, challenging feedback that helps the user arrive at better answers, rather than merely affirming their premises.
