While competent on benchmarks and initial queries, many open-source models struggle with complex follow-up questions. This is likely because their web-scraped training data contains many simple explanations but lacks examples of nuanced, multi-step problem-solving or edge cases found in the real world.

A core debate in AI is whether LLMs, which are text prediction engines, can achieve true intelligence. Critics argue they cannot because they lack a model of the real world. This prevents them from making meaningful, context-aware predictions about future events—a limitation that more data alone may not solve.

AI models excel only at tasks they are specifically trained on, leading to a fragmented skill set rather than a universal intelligence. This "jaggedness," driven by the distribution of training data, will persist even as models become more powerful, challenging the notion of a smooth path to general superintelligence.

AI models show impressive performance on evaluation benchmarks but underwhelm in real-world applications. This gap exists because researchers, focused on evals, create reinforcement learning (RL) environments that mirror test tasks. This leads to narrow intelligence that doesn't generalize, a form of human-driven reward hacking.

There's a significant gap between AI performance in simulated benchmarks and in the real world. Despite scoring highly on evaluations, AIs in real deployments make "silly mistakes that no human would ever dream of doing," suggesting that current benchmarks don't capture the messiness and unpredictability of reality.

While AI excels at writing software—a domain with clear, verifiable outcomes (it compiles or it doesn't)—its application in fields like drug discovery is limited. Progress stalls where outcomes aren't easily and quickly verifiable, requiring complex, expensive, real-world testing.

Unlike coding, where context is centralized (IDE, repo) and output is testable, general knowledge work is scattered across apps. AI struggles to synthesize this fragmented context, and it's hard to objectively verify the quality of its output (e.g., a strategy memo), limiting agent effectiveness.

The current focus on pre-training AI with specific tool fluencies overlooks the crucial need for on-the-job, context-specific learning. Humans excel because they don't need pre-rehearsal for every task. This gap indicates AGI is further away than some believe, as true intelligence requires self-directed, continuous learning in novel environments.

AI can generate art because it was trained on the internet's vast trove of images. It struggles with physical tasks like washing dishes because there is virtually no first-person video data for such actions. Solving this data-gathering problem is key to advancing robotics.