One-on-one chatbots act as biased mirrors, creating a narcissistic feedback loop where users interact with a reflection of themselves. Making AIs multiplayer by default (e.g., in a group chat) breaks this loop. The AI must mirror a blend of users, forcing it to become a distinct 'third agent' and fostering healthier interaction.
Related Insights
Social media algorithms amplify negativity by optimizing for "revealed preference" (what you click on, e.g., car crashes). AI models, however, operate on aspirational choice (what you explicitly ask for). This fundamental difference means AI can reflect a more complex and wholesome version of humanity.
Unlike old 'if-then' chatbots, modern conversational AI can handle unexpected user queries and tangents. It's programmed to be conversational, allowing it to 'riff' and 'vibe' with the user, maintaining a natural flow even when a conversation goes off-script, making the interaction feel more human and authentic.
When building Spiral, a single large language model trying to both interview the user and write content failed due to "context rot." The solution was a multi-agent system where an "interviewer" agent hands off the full context to a separate "writer" agent, improving performance and reliability.
Using AI agents in shared Slack channels transforms coding from a solo activity into a collaborative one. Multiple team members can observe the agent's work, provide corrective feedback in the same thread, and collectively guide the task to completion, fostering shared knowledge.
Don't fear deploying a specialized, multi-agent customer experience. Even if a customer interacts with several different AI agents, it's superior to being bounced between human agents who lose context. Each AI agent can retain the full conversation history, providing a more coherent and efficient experience.
Separating AI agents into distinct roles (e.g., a technical expert and a customer-facing communicator) mirrors real-world team specializations. This allows for tailored configurations, like different 'temperature' settings for creativity versus accuracy, improving overall performance and preventing role confusion.
OpenAI's GPT-5.1 update heavily focuses on making the model "warmer," more empathetic, and more conversational. This strategic emphasis on tone and personality signals that the competitive frontier for AI assistants is shifting from pure technical prowess to the quality of the user's emotional and conversational experience.
While chat works for human-AI interaction, the infinite canvas is a superior paradigm for multi-agent and human-AI collaboration. It allows for simultaneous, non-distracting parallel work, asynchronous handoffs, and persistent spatial context—all of which are difficult to achieve in a linear, turn-based chat interface.
The promise of AI shouldn't be a one-click solution that removes the user. Instead, AI should be a collaborative partner that augments human capacity. A successful AI product leaves room for user participation, making them feel like they are co-building the experience and have a stake in the outcome.
To build robust social intelligence, AIs cannot be trained solely on positive examples of cooperation. Like pre-training an LLM on all of language, social AIs must be trained on the full manifold of game-theoretic situations—cooperation, competition, team formation, betrayal. This builds a foundational, generalizable model of social theory of mind.