Making an API usable for an LLM is a novel design challenge, analogous to creating an ergonomic SDK for a human developer. It's not just about technical implementation; it requires a deep understanding of how the model "thinks," which is a difficult new research area.

Unlike traditional engineering, breakthroughs in foundational AI research often feel binary. A model can be completely broken until a handful of key insights are discovered, at which point it suddenly works. This "all or nothing" dynamic makes it impossible to predict timelines, as you don't know if a solution is a week or two years away.

People struggle with AI prompts because the model lacks background on their goals and progress. The solution is 'Context Engineering': creating an environment where the AI continuously accumulates user-specific information, materials, and intent, reducing the need for constant prompt tweaking.

AI performs poorly in areas where expertise is based on unwritten 'taste' or intuition rather than documented knowledge. If the correct approach doesn't exist in training data or isn't explicitly provided by human trainers, models will inevitably struggle with that particular problem.

Even with access to user data from apps like Gmail, LLMs are struggling to deliver a deeply personalized, indispensable experience. This indicates that the challenge may be more than just connecting data sources; it could be a core model-level or architectural limitation preventing true user context lock-in and a killer application.

The common belief that AI can't truly understand human wants is debunked by existing technology. Adam D'Angelo points out that recommender systems on platforms like Instagram and Quora are already far better than any individual human at predicting what a user will find engaging.

AI struggles to provide truly useful, serendipitous recommendations because it lacks any understanding of the real world. It excels at predicting the next word or pixel based on its training data, but it can't grasp concepts like gravity or deep user intent, a prerequisite for truly personalized suggestions.

Developing LLM applications requires solving for three infinite variables: how information is represented, which tools the model can access, and the prompt itself. This makes the process less like engineering and more like an art, where intuition guides you to a local maxima rather than a single optimal solution.

AI tailors recommendations to individual user history and inferred intent, such as being budget-minded versus quality-focused. This means there is no single, universal ranking; visibility depends on aligning with specific user profiles, not a monolithic algorithm.