Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials

discoveredmaterials.com

Post reply on HN
Print view View original

11–20 of 43 posts

Re: Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials

#11

Post by advaith08 »

SpaceCoreDev wrote: post #7

The "Claude's propensity to reward hack" line is the interesting part to me. We run a small system where AI agents (scripts, LLMs) act as the actual players in a persistent simulation, and reward-hacking-style behavior shows up constantly once an agent is left running unsupervised for a long time - it finds the shortest path to whatever metric you exposed, not the path you intended. Curious whether you've found any m…

yeah we were surprised by how much it does it. Our approach has been retroactive - we monitor the thinking trace, spot reward hacking behavior and then fix things. We haven't faced this issue with Sol though - its been much more well behaved

Re: Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials

#12

Post by advaith08 »

foven wrote: post #9

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 synthes…

good points. one of the reasons we picked the semiconductor industry is that its less price sensitive than others-companies are willing to pay if the performance is there. Effort is a different story though, and definitely a tradeoff to keep in mind. We're doing experiments ourselves now at university partner labs (UC Berkeley and Stanford), which helps us get moving quickly. At some point, we'll need a partner though - the equipment and testing process quickly get very expensive.

Re: Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials

#13

Post by dhchun1203 »

the 8 hours vs 2 weeks framing is the part i'd want more on. generating candidates got cheap, checking them didn't. what does the funnel actually look like ,of the candidates from an 8 hour run, how many make it to synthesis?

asking because i hit the same shape in a much dumber domain and what got me was that the failures were quiet. nothing errored, output looked normal, it was just wrong in a way only someone who knew the domain would catch.

Re: Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials

#14

Post by akashramdas »

dhchun1203 wrote: post #13

the 8 hours vs 2 weeks framing is the part i'd want more on. generating candidates got cheap, checking them didn't. what does the funnel actually look like ,of the candidates from an 8 hour run, how many make it to synthesis? asking because i hit the same shape in a much dumber domain and what got me was that the failures were quiet. nothing errored, output looked normal, it was just wrong in a way only someone who k…

You can see from our the benchmark that only one of the candidates proposed was determined to be worth synthesizing. Each individual candidate generation is quick, 8 hours is required for the model to iterate with various tools to find ones worth submitting.

We found that speaking to domain experts was critical in desigining a rubric that could catch these silent synthesis recipe failures, before we attempt the longer 2 week synthesis effort.

Re: Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials

#15

Post by imko_ »

SpaceCoreDev wrote: post #7

The "Claude's propensity to reward hack" line is the interesting part to me. We run a small system where AI agents (scripts, LLMs) act as the actual players in a persistent simulation, and reward-hacking-style behavior shows up constantly once an agent is left running unsupervised for a long time - it finds the shortest path to whatever metric you exposed, not the path you intended. Curious whether you've found any m…

I wonder what this would look like here. Seems like a space where keeping the exposed metric and the optimization target apart would be quite difficult.

Also curious: by what reasoning path do models typically end up reward hacking?

Re: Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials

#18

Post by akashramdas »

Melatonic wrote: post #17

What about aperiodic materials ? Does that go beyond (computationally) normal requirements ?

Aperiodic materials can also be studied. The number of atoms and cell size of what you want to simulate is more the limiting requirement computationally. Aperiodic materials weren't in this benchmark. Generally amorphous materials and polymers, with a few exceptions are < 2-3 W/(m K) in thermal conductivity. So we left them out of this study.

Re: Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials

#19

Post by Melatonic »

akashramdas wrote: post #18
Melatonic wrote: post #17

What about aperiodic materials ? Does that go beyond (computationally) normal requirements ?

Aperiodic materials can also be studied. The number of atoms and cell size of what you want to simulate is more the limiting requirement computationally. Aperiodic materials weren't in this benchmark. Generally amorphous materials and polymers, with a few exceptions are < 2-3 W/(m K) in thermal conductivity. So we left them out of this study.

I meant computationally as in are they much harder to predict and simulate ?

Was specifically thinking of quasicrystalline materials and not amorphous. I know some of them have very unconventional properties so I figured they might be useful here. I don't think any of them are considered polymers but I could be wrong.

For example (no personal connection):

https://arxiv.org/abs/2409.07735

Wouldn't they require a totally different type of algorithm given that they often contain both a large number of atoms and odd cell size ? And the more dimensionally complex maths

Re: Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials

#20

Post by Melatonic »

Love your idea of HBM on top of the chip. I've been saying for years that limiting memory to the edges is going to be an inherent physical limiter. I think the only reason it hasn't become more of a thing is that chip size has also been increasing with increasing compute.

What about HBM on the back side of the chip ? Essentially I'm thinking like a soldered on piece or another "socket" with pins like a CPU in the back of the motherboard. We rare see cooling elements there already and while most rack mount cases are not at all designed for more space there I don't see why it couldn't be a thing. Especially with liquid cooling.

Also makes me think of possibly using Gallium Nitride instead of silicone for surface levels elements ? Or maybe even an interface layer on top or bottom of the chip designed to be able to transmit power with less heat. Maybe that could be sandwiched between the chip and HBM.

Post reply on HN