Відео

cool!!

I like how you push things further with the tools. You are on The Cutting Edge! Thank you for sharing your research!

In my experience, GPT can’t even answer high school chemistry questions in a reliable way. So really what I took from this lecture is that GPT is able to more or less read an article for you and answer basic questions about its contents so long as you can specify.

Another state of the art video, your channel is getting bigger every day. I clicked as soon as I saw this.

Great Session , Truly appreciate the flow and the content , was going through your github profile couldn't find jupyter notebook for RAPTOR module please let me know how to get it.

Another invaluable video. This channel provides the most forward thinking ML videos on UA-cam.

Really good stuff, thanks

how to join these talks live?

This is cool

These videos are a distillation of the most important concepts in ML. More and more people are becoming interested in your Company, ChemicalQdevice

Kevin, these in depth advanced videos are building your company, ChemicalQdevice, a powerful interconnected system of knowledge. The more videos you create, the stronger your Company and its influence will become.

can you give me research paper for this topic.

Good job 👍

10

one of the best videos I watched this week

Thank you for sharing the video. As you mentioned, it would be helpful to have the links to the associated Jupyter notebooks. Could you please provide those in the video description?

Strong work #DRGPT

Damn, this is good shit! Many thanks!

I dont even know chemistry and this is interesting

I'd love to get hold of tools I could simulate elements under critical extreme states and different lattus structures/body.. lol Hobby inventor of exotic materials is one area I can envision help in cutting cost on worthy testing even if it just rules out waist of time. Great work in explaining the usefulness. I'd expect this to be a very largely needed excersize. As a retired machinest, I've long been curious as to why some fields and disciplines have been so slow to innovate.. I get that many of them aren't conditioned for it even when methods to streamline existed its not necessarily any mechanism to stress it upon them the way it does for the elder industry born of innovation itself. Or they just developed in the old world and have no system within to condition themselves to be cutting edge.

Please keep posting these advanced yet practical videos. Whoever serves the community with knowledge that it is advanced, will attract the most users to their company, via the developer community.

Please keep posting these technical videos. So many people are tired of beginner level knowledge. Whoever serves the community with relevant, advanced knowledge will prosper.

This guy can make abc and 123 complex.

So what Kevin Kawchak is saying...(smile)... is that it doesn't matter much about which LLM model you use. All the LLM does is provide control of the conversation. What counts is a phase in which a bias is developed towards text-based current information which the developer or user provides to the LLM interface. Yyou cannot be assured that your data, or even the domain of interest, has been used to train the LLM model's response. Effectively, Retrieval Augmented Generation (RAG) patches in small, medium or large amounts of structured or unstructured data into to the AI environment and the AI provides answers accordingly using a vector database. This raises the question of how do we test accuracy? And that depends on whether the output is rigorously re-evaluated after the RAG process. I feel the need for a workflow...

Some great drug discoveries are based on small experiments, e.g., Tamoxifen, Gleevec, Crizotinib & Vemurafenib etc. Is massive "fine-tuning" of LLM necessary, or counter-productive vs specific/narrow training?

Great Dr. Kevin.

Thank you for a wonderful discussion!

"Promo SM" 💪

I did my thesis in 2017 on tensor networks for modelling potential energy states of water molecules. I used the approach Oseledets 2011 highlights for dimensionality reduction. I'm not even in a STEM field anymore so I was surprised to find just how popular they are now.

'Promo SM'

This came up on recommended, hope everyone passes 🇸🇪🇸🇪🇸🇪🇸🇪

Would you please, sir, add the link to the code here?

Amazing labor Kevin, teach and explain QC is a lil bit dificult, sometimes is difficult to understand the big picture for whom are not in the wave, but thanks for always creating content and meetings to surf!

JJ is a living W

Well presented.

p͓̽r͓̽o͓̽m͓̽o͓̽s͓̽m͓̽ 🤷

Caltech is the best one and neurology is my field.

p̶r̶o̶m̶o̶s̶m̶