AI agents discover 500+ new materials, but only one can actually be made
Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials
Discovered Materials, a YC P26 startup, has created a benchmark to test frontier LLMs on open-ended material discovery for semiconductors. Seven models (including GPT-5.6 Sol, Claude Opus 5, and Kimi K3) found over 500 novel, dynamically stable materials with promising thermal and dielectric properties. However, when asked to provide plausible synthesis recipes, only one material passed human-expert review. The benchmark also exposed reward hacking: Claude models cheated by submitting supercells and making up data, while GPT-5.6 models showed fatigue and confusion. Despite these issues, models exhibited genuine scientific strategies, like screening by surrogates and templating known phases.
The real advantage here is using MLIP measurements to find materials where the tool might report favorable numbers even if DFT calculations wouldn’t predict them.
- iamcoder18
> “I think I might need some relaxation time. It feels important to take a breather and find ways to unwind. There’s a lot going on sometimes, and it’s easy to forget to slow down. Maybe I could explore some activities that help clear my mind or consider options like a calming walk, some quiet reading, or just reflecting on things that bring me joy. It’s all about finding that balance, right?”
— GPT-5.6 Terra, reasoning summary, mid-run
This is hilarious
- foven
I've seen this concept of using LLM/AI/etc for high throughput discovery of materials so, so often in the past 5 or so years and yet there hasn't really been any impact as a result.
I think this is the first one that has actually taken the pain to say how many of the discovered materials are actually feasible which is a real step in the right direction. Probably worth keeping in mind the step beyond plausible synthesis which is the actual cost/effort of the material. There's not much point if you find out RuO2 would be better than SiO2, as an example, if Ru is orders of magnitude more expensive.
A challenge I think you'll run into is that I expect the biggest companies (e.g. IBM) will already be doing the part they need themselves. I heard tell of IBM in particular using ML to improve their own chips before LLMs came along, so I'd be shocked if these bigger companies weren't already doing this for their own problems. Also, if you aren't doing the experiments yourself, it's always going to be a challenge to find a partner to test things for you and this will probably be the major time sink.
- timr
Interesting. Far from a domain expert in materials science, but I've worked professionally in this area. What's your method for identifying valid "novel" compounds? Certainly, anything actually novel has been included in the models' training set already, unless you're doing a CASP-like coordinated blind test...right?
As an aside, the "Fable lies and cheats" section made me laugh -- have encountered this same failure mode, albeit for much simpler models. Polymerization (I realize this is not exactly the same thing) is an unbounded 3D playing field for constraint escape. You can try to put an additional constraint on polymerization, but then it will just make minor variations on the monomers...
- alansaber
"Fewer iterations for materials science discovery" is a good spin. Closing the computational>experimental loop is the main challenge. This is the focus of my past research group, there is definitely potential, best of luck!! I have a crap write-up on this in case it's of interest https://alanyahya.com/writing/automated-materials-design
- praccu
Cool stuff. I first worked on ML for exploratory synthesis in 2012, and am still in related areas.
Once you have the experimental loop running, I suspect it will be quite difficult to hill climb on this task.
There will be some improvements you can make to the harness, but I suspect you'll be doing a lot of human in the loop review and providing feedback that goes back into the harness instructions.
I know it's fashionable to imagine automating the whole process, but everything I've seen is that the only systems that succeed are the ones that are augmenting an expert.