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

31–40 of 43 posts

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

#31

Post by advaith08 »

whattheheckheck wrote: post #26

Seems like this is a super hot direction goodluck Have you seen https://arxiv.org/pdf/2605.04375 https://arxiv.org/abs/2307.07522

thanks for sharing! We think the Experiments-as-code path is not the right approach. the beauty of LLMs is their ability to ingest and reason over unstructured data - they remove the need for formalizing experiments. We tried using declarative templates to document our experiments, but realized that most of the interesting insights (for example, how viscous a liquid feels) is easier described by ranting about the experiment to a LLM, than formalizing it via constructs/code.

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

#32

Post by advaith08 »

praccu wrote: post #30

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 fashi…

yeah, the tricky thing about the experimental loop is that: 1. its very difficult to do it in a reproducible manner (the same experiment done twice often gives different results due to small undocumented changes) 2. its expensive to do at scale.

Both of these properties make it hard to hill climb on experiment. What's worked for us so far is precisely what you said - having human experts review and provide feedback. we distil their reviews into rubrics, and have LLMs act as proxy experts using these rubrics. We expect the models will hill climb using this approach, and will reach (close to) human expert level by doing this.

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

#33

Post by areoform »

advaith08 wrote: post #11
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

How do you have access to the thinking trace?

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

#35

Post by chrisjj »

advaith08 wrote: post #31
whattheheckheck wrote: post #26

Seems like this is a super hot direction goodluck Have you seen https://arxiv.org/pdf/2605.04375 https://arxiv.org/abs/2307.07522

thanks for sharing! We think the Experiments-as-code path is not the right approach. the beauty of LLMs is their ability to ingest and reason over unstructured data - they remove the need for formalizing experiments. We tried using declarative templates to document our experiments, but realized that most of the interesting insights (for example, how viscous a liquid feels) is easier described by ranting about the exp…

Pure vibe-sciencing.

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

#36

Post by advaith08 »

areoform wrote: post #33
advaith08 wrote: post #11

Earlier quoted context omitted.

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

How do you have access to the thinking trace?

we have access to the thinking trace summaries, not the raw traces

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

#37

Post by isoprophlex »

iamcoder18 wrote: post #25

> “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, reason…

These are probably canaries to help detect model distillation by competitors

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

#39

Post by fabijanbajo »

package thermals end up setting the facility water bill.. what heat rejection costs in power and water mostly comes down to how cold the loop has to be: cold needs chillers and evaporative assist, warm can run on dry coolers. so resistance removed between die and coolant is headroom to run the loop warmer. curious if that's where your materials sit, and whether customers take the win as warmer supply temps or just more TDP..

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

#40

Post by agenticworldcup »

> Our business model: We aim to license and sell IP on the materials we discover, as well as the IP on how to make these materials. We're also exploring an alternate business model where we sell the harness+tools we use to discover materials to semiconductor and chemical companies, allowing them to discover materials on their own. We're leaning towards the latter to start, but we expect that we'll do both in the long run.

This is cool! Question though: If you have the keys to the kingdom, why wouldn't you just spin up compute + Agents to do auto-discovery of new materials over time? You would then be able to monopolize IP to the materials themselves, and be the sole supplier.

Post reply on HN