Brandon White
@bwhite5290Best Seven Foot ML Engineer in the World!
Similar User
@bitsinbio
@ceghadban
@davidycli
@velvetatom
@AlfredoAndere
@ai_luce
@LevelVC
@BrianHie
@subaita_rahman
@shelbynewsad
@beckypferdehirt
@nabsicle
@JorgeCondeBio
@ceeceeboom
@BigHatBio
We have reached a tipping point. Societal and technological pressures are sparking a shift from animal testing to AI. Animal testing is currently a pillar of biomedical research. While animal testing has been responsible for tremendous advancements in human health and…
Introducing Torso, a bimanual android actuated with artificial muscles.
This week on Barrchives, I chat with @rauchg (Founder and CEO of @Vercel) about how Vercel is changing the way frontend developers work. We discuss the motivation and process behind building Vercel’s AI products (@v0 and AI SDK), and how AI will enable a more personalized web and…
Many new machine learning tools for protein engineering have popped up in the last year. In these early days, it might be unclear how to actually use them for real molecular design tasks in industry. We demonstrate how to engineer a cholesterol drug and plastic degrading…
Chai-1: Impressive results in our hands. biorxiv.org/content/10.110… #compchem
To commandeer a saying from @ilyasut… Everything that sounds like it should work does work and if it doesn’t that just means you don’t understand a detail yet.
This is a significantly larger problem in biochemical experimentation. Human's choice of only publishing what makes a good story hurts models. We need to give models both the "positive" and "negative" data.
Terence Tao is spot on, AI models need more data on failure and what doesn’t work
BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Chemistry with one half to David Baker “for computational protein design” and the other half jointly to Demis Hassabis and John M. Jumper “for protein structure prediction.”
Riding in a Waymo the last time I was in SF is easily my favourite AI product experience so far. I think other industries, including biopharma, have a lot to learn from the successful build-up and roll-out of self-driving vehicles. We write about four transferable lessons here
What life science can learn from self-driving: convoke.bio/from-self-driv…
NVIDIA CEO: "IT'S IMPOSSIBLE" TO WIN AI RACE WITHOUT NUCLEAR Today in Washington DC @Nvidia CEO Jenson Huang said this when asked by @ChrisBarnardDL his thoughts on AI. Taiwan, where Jenson makes his chips, is on the edge of a grid crisis from closing its nuclear plants early.
honest to god I heavily fw any VC who agrees to meet on a weekend. absolute baller. deserves allocation in everything.
Nextflow is the most popular language to write and scale bioinformatics workflows. We have listened to and pledge our support to the community. LatchBio is releasing a native Nextflow integration. New tools to develop + host workflows for scientific teams.
In a world of Snowflake, Databricks, and LLMs… scientists still love to use spreadsheets. I’m talking about multi-tab, multi-colored spreadsheets with merged cells and plate layouts. While these are useful when recording experimental data or planning the next experiment, they…
A good test for any structure prediction model is its predictive accuracy for novel entrants to the PDB. I just ran Chai-1 on structure 9CBK released yesterday on the PDB (and importantly not yet included in the training set for Chai-1). 🖥️🧬 Chai-1 predicted 9CBK's…
We’re excited to introduce @ChaiDiscovery and release Chai-1, a foundation model for molecular structure prediction that performs at the state-of-the-art across a variety of drug discovery tasks We're releasing inference code, weights & a web interface: chaidiscovery.com/blog/introduct…
Today we’re launching @chaidiscovery, led by @joshim5 & his polymathic world class cofounders. We’re also open sourcing Chai-1: a state of the art frontier model for biomolecular interactions. @_DimensionCap has co-led the founding round alongside Thrive & OpenAI
Renegade, the first on-chain dark pool, is live on Arbitrum. Fully-private trading with zero MEV, slippage, or price impact. Dark pools account for nearly half of the TradFi market, and Renegade unlocks dark pools for DeFi — renegade.fi Here's how Renegade works 🧵
The sweet spot is going to be bigger small molecules (macrocycles, protacs, glues) and smaller peptides (glp1, etc). Drug discovery is going to experience a renaissance here. The training data is there, the therapeutic benefit is there, and the cost/supply is there. Underhyped.
As small molecule drugs become larger, biologics become smaller, and peptide therapeutics gain adoption, how will it act as a forcing function for new representations in ML applied to molecular design? Do we default to atoms/electrons vis-a-vis neural network potentials? Does…
United States Trends
- 1. Good Monday 36 B posts
- 2. #MorningJoe N/A
- 3. Joe and Mika N/A
- 4. #MondayMotivation 12,3 B posts
- 5. #MondayVibes 2.011 posts
- 6. Bengals 82,8 B posts
- 7. #MondayMood 1.525 posts
- 8. Chargers 71,9 B posts
- 9. #18Nov 1.495 posts
- 10. Victory Monday N/A
- 11. WWIII 197 B posts
- 12. 60 Minutes 38,7 B posts
- 13. Herbert 36,5 B posts
- 14. McPherson 12,7 B posts
- 15. Myron 12,9 B posts
- 16. Joe Burrow 22,9 B posts
- 17. Margaret Thatcher 5.627 posts
- 18. TAEYEON 60 B posts
- 19. Rusia 125 B posts
- 20. Scotty 10,8 B posts
Who to follow
-
Bits in Bio
@bitsinbio -
Chris Ghadban
@ceghadban -
David Li
@davidycli -
Tess van Stekelenburg
@velvetatom -
Alfredo Andere
@AlfredoAndere -
Luciano Arango
@ai_luce -
Level Ventures
@LevelVC -
Brian Hie
@BrianHie -
Subaita Rahman
@subaita_rahman -
Dr. Shelby
@shelbynewsad -
Becky Pferdehirt
@beckypferdehirt -
Nabiha Saklayen
@nabsicle -
Jorge Conde
@JorgeCondeBio -
Cee Cee Schnugg
@ceeceeboom -
BigHat Biosciences
@BigHatBio
Something went wrong.
Something went wrong.