Optimizing a single end-to-end RL agent to synthesize novel materials is impossible when physical synthesis and furnace cycles take days. Long rollout times, hardware delays, and high physical noise prevent variance reduction across runs. Rather than targeting end goals like finding superconductors in a single loop, Periodic Labs breaks workflows into discrete agents rewarded on specific sub-tasks, such as identifying crystal phases from raw X-ray diffraction scans.

Unlike language models trained on the internet, AI for materials science overcomes data scarcity and unreliability (e.g., conflicting literature) with a closed loop. The system actively directs experiments, analyzes grounded results for patterns, and uses that new data to drive the next cycle.

Moving beyond simulation, Genesis uses a cycle where their AI proposes molecules, a pharma partner synthesizes and tests them in a wet lab, and the experimental outcomes are used as feedback to retrain the generative model. This is akin to RLHF but with physical experiments.

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.

A "software-only singularity," where AI recursively improves itself, is unlikely. Progress is fundamentally tied to large-scale, costly physical experiments (i.e., compute). The massive spending on experimental compute over pure researcher salaries indicates that physical experimentation, not just algorithms, remains the primary driver of breakthroughs.

Unlike many AI fields obsessed with compute, the primary bottleneck in materials discovery is the speed and cost of running physical experiments. Progress depends on experimental throughput, not just bigger models or more GPUs.

The ultimate bottleneck for fully automated scientific discovery is performing physical experiments. The ideal breakthrough would be a universal "everything lab" that could execute any physical experiment on demand, closing the loop between computational hypothesis and real-world validation.

Friedberg and Sacks explain that AI advances much faster in mathematics and software engineering because their reasoning loops are completely testable in software. Unlike biology or logistics, these disciplines require no physical lab testing or human-in-the-loop validation, enabling continuous automated reinforcement learning.

Instead of relying on digital proxies like code graders, Periodic Labs uses real-world lab experiments as the ultimate reward function. Nature itself becomes the reinforcement learning environment, ensuring the AI is optimized against physical reality, not flawed simulations.