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.

Pre-training on internet text data is hitting a wall. The next major advancements will come from reinforcement learning (RL), where models learn by interacting with simulated environments (like games or fake e-commerce sites). This post-training phase is in its infancy but will soon consume the majority of compute.

Training AI agents to execute multi-step business workflows demands a new data paradigm. Companies create reinforcement learning (RL) environments—mini world models of business processes—where agents learn by attempting tasks, a more advanced method than simple prompt-completion training (SFT/RLHF).

AI labs like Anthropic find that mid-tier models can be trained with reinforcement learning to outperform their largest, most expensive models in just a few months, accelerating the pace of capability improvements.

Beyond supervised fine-tuning (SFT) and human feedback (RLHF), reinforcement learning (RL) in simulated environments is the next evolution. These "playgrounds" teach models to handle messy, multi-step, real-world tasks where current models often fail catastrophically.

Reinforcement Learning with Human Feedback (RLHF) is a popular term, but it's just one method. The core concept is reinforcing desired model behavior using various signals. These can include AI feedback (RLAIF), where another AI judges the output, or verifiable rewards, like checking if a model's answer to a math problem is correct.

The transition from supervised learning (copying internet text) to reinforcement learning (rewarding a model for achieving a goal) marks a fundamental breakthrough. This method, used in Anthropic's Opus 3 model, allows AI to develop novel problem-solving capabilities beyond simple data emulation.

The distinction between imitation learning and reinforcement learning (RL) is not a rigid dichotomy. Next-token prediction in LLMs can be framed as a form of RL where the "episode" is just one token long and the reward is based on prediction accuracy. This conceptual model places both learning paradigms on a continuous spectrum rather than in separate categories.

Unlike math or code with cheap, fast rewards, clinically valuable biology problems lack easily verifiable ground truths. This makes it difficult to create the rapid reinforcement learning loops that drive explosive AI progress in other fields.