Even a specialized task like coding involves a wide range of human-like interaction: brainstorming, searching, and more. This "AGI-completeness" means a powerful general model with a good "bedside manner" can outperform a narrowly specialized one, complicating the strategy for vertical AI apps.

Specialized coding models often fail because a developer's workflow isn't just writing code; it's a complex conversation involving brainstorming, compliance, and web research. The best coding assistants are the most generalist models because every complex task has AGI-like qualities.

A Rice PhD showed that training a vision model on a game like Snake, while prompting it to see the game as a math problem (a Cartesian grid), improved its math abilities more than training on math data directly. This highlights how abstract, game-based training can foster more generalizable reasoning.

The structured, hierarchical nature of code (functions, libraries) provides a powerful training signal for AI models. This helps them infer structural cues applicable to broader reasoning and planning tasks, far beyond just code generation.

The industry was surprised to learn that the tool-calling and problem-solving DNA of coding agents provides the necessary foundation for general-purpose agents. This was not the anticipated route to AGI, which labs hadn't explicitly trained for, yet it has become the dominant and most promising approach.

Current AI models resemble a student who grinds 10,000 hours on a narrow task. They achieve superhuman performance on benchmarks but lack the broad, adaptable intelligence of someone with less specific training but better general reasoning. This explains the gap between eval scores and real-world utility.

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.

AI's ability to code seems like advanced reasoning, but it's actually just navigating the most complete archive of human knowledge ever created. Programming's version control, documentation, and forums provide a perfectly mapped territory for AI to search, not a complex problem for it to solve through intelligence.