When AI models achieve superhuman performance on specific benchmarks like coding challenges, it doesn't solve real-world problems. This is because we implicitly optimize for the benchmark itself, creating "peaky" performance rather than broad, generalizable intelligence.

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.

Public leaderboards like LM Arena are becoming unreliable proxies for model performance. Teams implicitly or explicitly "benchmark" by optimizing for specific test sets. The superior strategy is to focus on internal, proprietary evaluation metrics and use public benchmarks only as a final, confirmatory check, not as a primary development target.

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.

Don't trust academic benchmarks. Labs often "hill climb" or game them for marketing purposes, which doesn't translate to real-world capability. Furthermore, many of these benchmarks contain incorrect answers and messy data, making them an unreliable measure of true AI advancement.

Karpathy criticizes standard reinforcement learning as a noisy and inefficient process. It assigns credit or blame to an entire sequence of actions based on a single outcome bit (success/failure). This is like "sucking supervision through a straw," as it fails to identify which specific steps in a successful trajectory were actually correct.

Karpathy identifies the AI community's 2010s focus on reinforcement learning in games (like Atari) as a misstep. These environments were too sparse and disconnected from real-world knowledge work. Progress required first building powerful representations through large language models, a step that was skipped in early attempts to create agents.

The most fundamental challenge in AI today is not scale or architecture, but the fact that models generalize dramatically worse than humans. Solving this sample efficiency and robustness problem is the true key to unlocking the next level of AI capabilities and real-world impact.

As reinforcement learning (RL) techniques mature, the core challenge shifts from the algorithm to the problem definition. The competitive moat for AI companies will be their ability to create high-fidelity environments and benchmarks that accurately represent complex, real-world tasks, effectively teaching the AI what matters.