Pinned
After a few years of procrastination, I've updated my textbook. Changes:
1. Tensorflow -> PyTorch
2. Darkmode
3. Added scaffold split section
4. Fixed many typos
Andrew White ๐ฆโโฌ
6,932 posts
Andrew White ๐ฆโโฌ
@andrewwhite01
Automating science. Cofounder @EdisonSci. Cofounder @FutureHouseSF. Prof of chem eng @UofR (on sabbatical).
- I've been writing research articles for over 10 years now and one of the hardest parts is writing consistently and efficiently without procrastinating. I'm going to share some of my tips here ๐งต 1/10
- Replying to @andrewwhite01[placeholder for when I've finished]
- In academia, we don't say "I love you." We say "minor revisions." And I think that's really beautiful.
- After two years of work, weโve made an AI Scientist that runs for days and makes genuine discoveries. Working with external collaborators, we report seven externally validated discoveries across multiple fields. It is available right now for anyone to use. 1/5
- I packed-up a full-text paper scraper, vector database, and LLM into a CLI to answer questions from only highly-cited peer-reviewed papers. Feels unreal to be able instantly get answers by an LLM "reading" dozens of papers. 1/2
00:00 - Sometimes people ask me advice about academia. I have no idea what I'm doing 80% of the time. All my PI proposals in last 2 years have been rejected. In my entire academic career, I've never been able to get a paper reviewed at JACS, Nat Chem, PNAS, etc. 1/2
- About 75% of doing a PhD is getting your python environment set-up
- Apple's AI researchers have embraced a kind of anti-LLM cynic ethos, publishing multiple papers trying to argue that reasoning LLMs are somehow limited/cannot generalize. Apple also has the worst AI products (Siri, Apple Intlligence). No idea what their "strategy" is here
- Packaged our algorithm to design binding peptides into a simple colab. Enter a protein sequence, indicate where you want the peptide to bind, and in a few minutes you'll have a peptide predicted to tightly bind via AlphaFold + Bayesian Optimization. 1/2 colab.research.google.com/github/ur-whitโฆ
- I just paid $60 to embed the text of the entire lord of the rings trilogy so I could have GPT answer a question I've wondered my whole evening: Do the people of Middle Earth poop? 1/6
- We report a model that can go from natural language instructions, to robot actions, to synthesized molecule with an LLM. We synthesized catalysts, a novel dye, and insect repellent from 1-2 sentence instructions. This has been a seemingly unreachable goal for years! 1/3
- This is the worst day ever to launch our reasoning model. We're just gonna announce it fresh next week. Everyone please act surprised.
- The average PhD student spends 8 months of their academic career learning about CUDA drivers, conda, pip, setup_tools, and brew. Feels solved now with GPT-4