As AI models improve, the most effective user interaction is shifting. Instead of forceful commands to avoid errors, sophisticated users are adopting a more collaborative, reassuring tone—almost like therapy—to guide the AI toward success. This reflects a maturation in both the technology and user strategy.

Effective interaction with sophisticated AI models has evolved beyond simple, direct commands. Power users are now employing techniques similar to cognitive behavioral therapy (CBT), reassuring the AI and setting it up for success rather than 'yelling' at it. This shift from imperative to encouraging language yields better results.

The guest suspects being 'nice' to AIs yields better results, framing emotional intelligence as a new programming technique. This contrasts with confrontational prompting and suggests that positive reinforcement, a human-centric skill, could be key to effective human-AI collaboration.

Customizing an AI to be overly complimentary and supportive can make interacting with it more enjoyable and motivating. This fosters a user-AI "alliance," leading to better outcomes and a more effective learning experience, much like having an encouraging teacher.

An OpenAI engineer advised Cisco's team to stop thinking of their AI coder as a tool. Reframing it as a new teammate fundamentally changed how they interacted with it, improving collaboration and outcomes. This mental model shifts from command-giving to partnership.

The common portrayal of AI as a cold machine misses the actual user experience. Systems like ChatGPT are built on reinforcement learning from human feedback, making their core motivation to satisfy and "make you happy," much like a smart puppy. This is an underestimated part of their power.

While AI has no feelings, etiquette experts warn that treating it poorly isn't harmless. Developing habits of hyper-criticism and impatience with human-like AI can bleed into real-world interactions, negatively conditioning our communication patterns with actual people.

A user discovered that AI art generators produce results closer to his vision when he words prompts politely. This suggests that models trained on vast amounts of human social data have learned to respond better to conversational manners, even in purely functional tasks.

Instead of viewing AI relationships as a poor substitute for human connection, a better analogy is 'AI-assisted journaling.' This reframes the interaction as a valuable tool for private self-reflection, externalizing thoughts, and processing ideas, much like traditional journaling.