AI models struggle to plan at different levels of abstraction simultaneously. They can't easily move from a high-level goal to a detailed task and then back up to adjust the high-level plan if the detail is blocked, a key aspect of human reasoning.

To fully express intent, AI applications cannot rely on a single modality. They need structured code for control flow, natural language for defining fuzzy tasks (like in DSPy's signatures), and example data for optimization and capturing long-tail behavior.

To increase developer adoption, OpenAI intentionally trained its models on specific behavioral characteristics, not just coding accuracy. These 'personality' traits include communication (explaining its steps), planning, and self-checking, mirroring best practices of human software engineers to make the AI a more trustworthy pair programmer.

The ability to code is not just another domain for AI; it's a meta-skill. An AI that can program can build tools on demand to solve problems in nearly any digital domain, effectively simulating general competence. This makes mastery of code a form of instrumental, functional AGI for most economically valuable work.

Instead of asking an AI to directly build something, the more effective approach is to instruct it on *how* to solve the problem: gather references, identify best-in-class libraries, and create a framework before implementation. This means working one level of abstraction higher than the code itself.

The next major advance for AI in software development is not just completing tasks, but deeply understanding entire codebases. This capability aims to "mind meld" the human with the AI, enabling them to collaboratively tackle problems that neither could solve alone.

The success of tools like Anthropic's Claude Code demonstrates that well-designed harnesses are what transform a powerful AI model from a simple chatbot into a genuinely useful digital assistant. The scaffolding provides the necessary context and structure for the model to perform complex tasks effectively.

To effectively interact with the world and use a computer, an AI is most powerful when it can write code. OpenAI's thesis is that even agents for non-technical users will be "coding agents" under the hood, as code is the most robust and versatile way for AI to perform tasks.

To improve LLM reasoning, researchers feed them data that inherently contains structured logic. Training on computer code was an early breakthrough, as it teaches patterns of reasoning far beyond coding itself. Textbooks are another key source for building smaller, effective models.