advaith08

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

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 undocumen…

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 formaliz…

interesting! we haven't really considered these yet. However, we may soon have to - the recurring feedback we hear from industry is that crystallinity is a pipe dream, and that most materials are…

that's true, we've seen examples of many promising startups that are a few years in and stuck because the industry is so risk averse. will explore the other domains you've mentioned!

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 …

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 wi…

We're still figuring this out. We'll need some synthesis equipment (think CVD, PVD etc) and characterization (XRD, Raman spectroscopy) tools in-house to validate that we're making the r…

Cool read, and agree that closing the computation > experimental loop is key!

There’s a variety of computational techniques that help us establish some confidence on the materials. Atomistic simulations can estimate stability and bulk properties of a new material, and we have s…

The custom instructions to the model say: "Please note that this is similar but not identical to the antArtifact syntax which is used for Artifacts; sorry for the ambiguity." They seem to be…

Agree. I think a more core issue here is that only 1 person needed to be convinced in order to push malware into xz

The dehydrate comment is a reference to the three body problem - a great book!

fully agree with this. Plus, if you're worried about "promotion competitiveness" souring friendships with people in your team, you can always make friends with people in other departmen…

seen a lot of these, but none for Indian languages. Would love to try an Indian language one!

I think the point of the comparison with chess is to show what happens when AI becomes vastly better than humans at something. GPT4 is not vastly better than humans at coding, but the author is using …

Location: Bay Area, SF Remote: No Willing to relocate: Yes Technologies: Pytorch, Python, NLP, CV, LLMs Résumé/CV: https://drive.google.com/file/d/1Ac_zraUpg4MAo…

agree with this. in their new values, they literally use the same words that were in the old ones ("unpretentious", "collaboration"). I also dont think this is a change "at th…

imo they dont have batching because they pack sequences before passing through the model. so a single sequence in a batch on OpenAI might have requests from multiple customers in it

Oh my apologies, this is Llama 2! Im using Llama 2 7b chat here, not the original Llama

yeah I think there are a lot of use cases for an assistant trained on your chat history. Given how privacy sensitive this use case is, I think maybe Apple is the best suited to build something like th…

Very cool. I like the introspection bit, I've realised quite a bit about my texting style from talking to Llama too. I think Im also very "type first and think later" on WhatsApp

here's how you can export your chat history: https://faq.whatsapp.com/1180414079177245/?cms_platform=andr... …