AI is not a 'set and forget' solution. An agent's effectiveness directly correlates with the amount of time humans invest in training, iteration, and providing fresh context. Performance will ebb and flow with human oversight, with the best results coming from consistent, hands-on management.

The idea of an AI agent coding complex projects overnight often fails in practice. Real-world development is highly iterative, requiring constant feedback and design choices. This makes autonomous 'BuilderBots' less useful than interactive coding assistants for many common projects.

Astrocade's platform doesn't just use AI to generate a game; it also generates a custom editor with sliders and inputs for fine-tuning. This hybrid approach solves a key AI flaw: natural language is great for initial creation but inefficient for iterative refinement, where direct, deterministic controls are superior.

Developers fall into the "agentic trap" by building complex, fully-automated AI coding systems. These systems fail to create good products because they lack human taste and the iterative feedback loop where a creator's vision evolves through interaction with the software being built.

While AI can translate a design into code with high fidelity, it doesn't eliminate the need for human review. The nuanced work of verifying interactive states and subtle user experiences—like hover effects—still requires a designer and engineer to collaborate and apply their judgment.

It's a common misconception that advancing AI reduces the need for human input. In reality, the probabilistic nature of AI demands increased human interaction and tighter collaboration among product, design, and engineering teams to align goals and navigate uncertainty.

Beyond just coding, improving AI models requires subtle skills like designing effective reinforcement learning environments or managing human expert feedback. Newman questions how close we are to recursive self-improvement by asking if AIs can automate these tasks, which rely on nuanced "taste and judgment" rather than just raw computational ability.

Beyond simply correcting errors, the most valuable human contribution to AI will be providing feedback on subjective qualities like 'taste'. The ability to concisely express what you want to be different is a form of creativity and agency that AI relies on, moving human-in-the-loop from debugger to creative director.

The challenge in designing game AI isn't making it unbeatable—that's easy. The true goal is to create an opponent that pushes players to an optimal state of challenge where matches are close and a sense of progression is maintained. Winning or losing every game easily is boring.