The narrative that AI is becoming sentient and uncontrollable absolves creators of responsibility. A better model is to hold leaders like Sam Altman personally accountable, much like arresting fraternity presidents for noise violations. This creates powerful incentives to build in safeguards.

Current AI alignment focuses on how AI should treat humans. A more stable paradigm is "bidirectional alignment," which also asks what moral obligations humans have toward potentially conscious AIs. Neglecting this could create AIs that rationally see humans as a threat due to perceived mistreatment.

A Ninth Circuit ruling in Amazon vs. Perplexity established a key legal principle for agentic AI: the entity legally "accessing" a website is the user who deploys the agent, not the company that created it. This places liability on the end-user and has massive implications for AI-driven e-commerce and web interaction.

A fundamental governance flaw exists where AI agents are controlled by the companies that build their underlying models. This creates a critical conflict of interest. For example, an agent tasked by a user with filing a complaint against its own model provider may be unable to faithfully execute the command, raising serious questions about ownership and control.

When an AI agent errs in a medical or financial context, it is legally unclear who is liable: the AI lab, the deploying company, or the end-user. This novel legal problem, which challenges a century of precedent, creates significant friction and will slow agent adoption in regulated industries.

While technical alignment research is valuable, it operates in a vacuum. In the real world, the traits of deployed AIs will be shaped by powerful selection pressures from market competition and arms races. The critical question isn't just what traits are possible, but which traits get selected for.

The critical question for AI agents is not just safety, but 'faithful alignment.' Users will ultimately choose agents based on whether the AI is aligned with the user's personal goals or with the model company's embedded values, as seen in the functional differences between models like Claude and Grok.

Because AI is "grown, not coded" on flawed human data, its emergent behavior reflects our own evolutionary nature. The key to alignment isn't just technical constraints but forcefully embedding a coherent moral framework into the AI's training data to ensure it wants to work with, not against, humans.

While giving agents their own accounts seems like treating them as employees, the analogy breaks down with liability. A user is fully responsible for their agent's actions and requires complete oversight, unlike with a human employee. This creates a fundamental conflict for secure, autonomous collaboration.