A conversation with Claude

Seems like everyone is publishing their conversations with Claude these days. Vanity Fair reporter Joe Hagan published a fake Claude-generated “interview” with Anthropic CEO Dario Amodei.¹ Bernie Sanders published a video of himself talking to Claude about AI and privacy. So I thought, why don’t I publish one of my own conversations with Claude? I’m afraid this one isn’t as spicy as those others, but you might still find it fun.

This particular conversation started out as me asking Claude about potential AI discoveries in materials science. The discussion then segues into the more general question of what types of scientific research AI is best at, and what areas of research might see the biggest acceleration from AI. It turns out that I’m actually more bullish than Claude on AI’s capacity for breakthrough ideas — Claude thinks humans will retain the edge in creativity and invention, but I bet AI will get good at this very quickly.

My bet is that the constraints on AI science will be a subset of the constraints on human science. Whenever data is sparse, both AI and humans will struggle to do more than come up with conjectures (and ideas for how to gather more data). And when humans have already discovered most of what there is to know about some natural phenomenon, AI won’t be able to get much farther because there just isn’t much farther to go.

I do suspect, however, that AI is going to discover some truly groundbreaking science that humans never could have discovered on their own. I explained why in my New Year’s essay three years ago:

The third magic Noah Smith · January 1, 2023 Read full story

Basically, human science is all about compressibility. We take some natural phenomenon — say, conservation of momentum — and we boil it down to a simple formula. That formula is very easy to communicate from person to person, and it’s also very easy to use. These are what we call the “laws of nature”.

But there’s no reason why every natural principle needs to obey simple laws that can be written down in a few lines. There could be more complex patterns in nature — too complex for a human to hold in their mind, or even notice in the first place, but stable and useful nonetheless. LLMs themselves are a good example of such a pattern — we figured out how to create and apply human language without ever being able to write down simple “laws” of how it worked.

What if there are other complex-but-useful patterns in other domains, like materials science and biology? If they exist, I think AI will be able to find them and apply them. The question — as Claude notes near the end of our discussion — is whether AI would be able to communicate those laws to humans. The answer is: Probably not. Just like a dog will never be able to understand quantum mechanics, humans may never be able to understand some of the scientific principles that AI discovers and harnesses.

Anyway, it was a fun discussion. Claude is notoriously sycophantic — it’s always telling me my ideas are brilliant and I’m asking exactly the right questions. But it also makes some very thoughtful points. The whole conversation feels like a late-night discussion in the hall of a freshman dorm. That’s not an insult; for many of us, those are some of the most fun conversations we ever have in our entire lives.

I also learned what topological materials are, which is pretty awesome. And I managed to work in a reference to Star Trek: The Next Generation.

Noah: What are the 10 to 20 most transformative advances in materials science that might be made with the aid of AI in the next few decades?

Claude: Great question — this sits right at the intersection of AI capability scaling and physical-world impact. Here’s my best attempt at a list, roughly ordered from nearer-term/higher-confidence to longer-term/more speculative:

1. Room-temperature (or near-room-temperature) superconductors. AI-driven inverse design of crystal structures could dramatically accelerate the search through composition space. Even a superconductor that works at, say, -20°C at ambient pressure would be civilization-altering for energy transmission, maglev, and fusion magnets.

2. Solid-state electrolytes for batteries. AI screening of candidate materials (sulfides, oxides, halides) for ionic conductivity, electrochemical stability, and manufacturability could crack the solid-state battery problem, giving us energy densities 2-4x lithium-ion with no fire risk.

3. Direct air capture sorbents. The combinatorial space of metal-organic frameworks (MOFs) and porous polymers is enormous — exactly the kind of problem where ML surrogate models for DFT calculations shine. Finding a sorbent with the right CO₂ binding energy, water stability, and regeneration energy could make DAC economically viable at scale.

4. Catalysts for green hydrogen and ammonia. Replacing platinum-group metals in electrolyzers and finding alternatives to the Haber-Bosch process (which consumes ~1-2% of global energy) via AI-designed catalysts — perhaps single-atom catalysts or high-entropy alloys — would be transformative for decarbonization.

5. Ultra-high-performance structural alloys. AI exploration of high-entropy alloy (HEA) composition spaces could yield materials with unprecedented combinations of strength, ductility, and corrosion resistance — relevant for everything from jet engines to deep-sea infrastructure.

6. Programmable self-healing materials. AI could design polymer networks or composite architectures that autonomously detect and repair damage, extending infrastructure lifespans enormously. Think bridges, pipelines, and aircraft that fix their own micro-cracks.

7. Next-generation photovoltaic absorbers. Beyond perovskites — AI could identify stable, non-toxic, earth-abundant semiconductors with optimal bandgaps and defect tolerance, potentially pushing solar cell efficiency toward thermodynamic limits while being cheap to manufacture.

8. Designer proteins and biomimetic materials. Building on AlphaFold-style breakthroughs, AI-designed proteins could yield spider-silk-strength fibers, biological adhesives, self-assembling nanostructures, and enz