Making the future of medicine accessible to everyone. Buy peptides with no markup, direct from US pharmacies.
Austin, TX
Joined February 2015
- Tweets29
- Following36
- Followers58
- Likes98
Pinned Tweet
Medicine has spent a century treating the average patient.
The next century belongs to the individual.
Personalized medicine, care built around your biology, your data, and your goals, isn't a trend.
It's the direction the entire field is moving.
We're building the infrastructure for it.
Big Pharma might be sitting on one of the largest untapped AI training datasets in the world.
Decades of failed drugs, clinical trials, protein structures, assays, patient data, and experiments.
This will be a massive unlock as that data gets fed into modern AI models.
An AI system trained on more than 20,000 protein structures from pharmaceutical companies outperforms AlphaFold-like models that use only public data
go.nature.com/4gTSLaA
Friendly reminder that growth and longevity are usually competing biological priorities.
Muscle is great. Strength is great. And if you want to maximize muscle growth, periods of higher calories and anabolic modes make sense.
But a lot of the longevity findings in animals point will say the opposite. The less GH/IGF-1 signaling, less mTOR activity, and less time spent in “growth mode”, the better for longevity.
Basically, permanently maximizing anabolic signaling is very different from maximizing lifespan.
More great biotech progress.
AI is getting closer to letting doctors test cancer drugs on a virtual version of your tumor before giving them to you.
Researchers built an AI model of breast cancer cells that predicted their response to 81 previously unseen drugs with 88% accuracy.
They then tested it using tumor biopsies from 501 patients, and its predictions correlated with how patients actually responded to treatment.
It’s still early, but these sorts of virtual cell tests are getting more and more promising.
Model trained on millions of protein measurements can gauge drug effectiveness in tissue samples taken from people with triple-negative breast cancer.
go.nature.com/4hk7POR
This is one of the coolest use cases for AI coding tools.
There are thousands of hyper-specific problems like this that are obvious to the people who deal with them every day, but too niche for a software company to spend months building a solution.
Now a medical student can basically say, “This is how I wish I could learn anatomy,” and build the tool themselves.
GPT-6 Astra just solved a problem medical students have been facing for decades
Medical students have been working around the same three problems for decades. Someone talked to them, identified all three, and built a service with Astra that solves them in one tool.
The problems are structural. Flat anatomical diagrams strip depth out of organs entirely. CT cross-sections don't connect naturally to the overview diagrams students spend years memorizing. And reading a scan requires holding three mental models simultaneously - patient orientation, cross-section direction, and how every organ shape shifts through each layer.
Astra built a service that handles all three in one place. Not a better textbook. A spatial tool that connects the diagram, the CT view, and the 3D relationship together.
Medical education hasn't changed its core format in over a century. This might be the first tool designed around how anatomy is actually understood - not just displayed.
Incredibly exciting!
With AlphaFold we mapped the protein universe - now with AlphaGenome Atlas we’re charting the human genome. It can predict the impact of all 9 billion possible single-letter DNA variants, helping scientists better understand disease. Freely available for academic research: alphagenome.google/atlas
Most people hear “pig kidney” and think the goal is to replace a human kidney forever.
But, it doesn't have to.
When your kidneys fail, you can spend years on dialysis waiting for a human kidney.
In the US, average wait is about 4–5 years.
This genetically engineered pig kidney kept him off dialysis for 271 days. Then he got a human kidney.
If we can increase the total length the pig kidney (or some other one) works for, this is a massive improvement, since it would bridge the gap.
Transplanted pig kidney works in US man's body for record 271 days bbc.in/4yiumBg
The first hip surgery using the Apple Vision Pro was just completed by surgeons at Duke Health. This is an exciting step for VR/AR in surgery to achieve better results for patients.
ChatGPT can now connect to Epic and help clinicians make sense of a patient’s records.
This is a clear instance of AI moving from “a tool doctors use” to an intelligence layer integrated with the entire healthcare system.
Very exciting!
techcrunch.com/2026/09/01/ch…
The part you see is “mice don’t have to workout” (which admittedly is pretty cool).
But since most people don't read the full study, the cooler part is that they turned the extra muscle into a tiny gland. It sits under the skin, grows its own blood vessels, and makes parathyroid hormone or growth hormone for months.
So potentially, instead of a needle every morning, you could have a piece of your own muscle manufacture the missing protein for you. And just pumps it out like a little factory.
1 in 3 U.S. adults with type 2 diabetes already have biomarker evidence of heart damage they don’t know about.
Mounjaro is the first dual GIP/GLP-1 to cut CV death, heart attack, and stroke in high-risk Type 2 diabetes.
Another win for health.
The Food and Drug Administration cleared Mounjaro to lower cardiovascular risk in adults with type 2 diabetes and established heart disease, according to a statement from Lilly on Friday. bloomberg.com/news/articles/…
One of the most underrated parts of this is that Daraxonrasib was one of the first drugs selected for the Commissioner’s National Priority Voucher pilot.
That program is meant to compress the review of products that hit national health priorities. And it helped this get approved 6 months ahead of schedule.
This is a strong sign of potentially faster approvals down the line.
Breaking News: The FDA approved a first-of-its-kind pill that could substantially extend the lives of patients with pancreatic cancer. nyti.ms/4y6PdYr
In a recently published Nature Medicine study of 51 human trials and 16 epigenetic clocks, the interventions that most consistently slowed biological aging weren’t supplements.
They were lifestyle changes (diet + exercise) and certain drugs like metformin, semaglutide, and anti-TNF therapies.
Omega-3s and folate showed weaker, less consistent effects.
Boring basics still beat the hype.
Important development that it seems like people are missing:
We may be able to treat nut allergies with peptides.
The FDA just fast-tracked a peanut allergy treatment made of 7 tiny synthetic peptides.
They retrain the immune system to tolerate peanuts… without using actual peanut protein that can trigger reactions during treatment.
Because of that, it’s much safer than existing immunotherapy treatments. And would be delivered as a monthly injection.
Phase 2 data coming later this year.
If this works, it could change food allergy treatment.
🚨FDA NEWS🚨
The @US_FDA has granted fast track designation to PVX108, an #immunotherapy comprising seven synthetic #peanut-peptide fragments, according to a press release from Aravax.
vist.ly/5fwm5
Since Robert Waldinger was just named a TIME Longevity Leader, worth repeating one of the most important longevity findings ever:
The Harvard Study of Adult Development followed people for nearly 90 years.
The biggest predictor of health and happiness wasn’t supplements, biomarkers, or biological age clocks.
It was the quality of your relationships.
Invest in the people who will still be there decades from now.
Introducing TIME’s 2026 Longevity Leaders: 12 trailblazers on a mission to help us live longer, healthier lives time.com/collection/longevit…
Simulation has a proven track record of unlocking breakthroughs at a fraction of the real-world cost.
- Aerodynamics (wind tunnels + CFD).
- Climate models.
- Particle physics (Monte Carlo + Geant4).
Now cell biology is getting its turn.
Excited to see where this goes.
A personalized cancer vaccine just passed phase 3 trials for the first time ever.
And there are more like this in the pipeline:
• BioNTech’s autogene cevumeran (BNT122) – Phase 2 in colorectal & pancreatic
• Gritstone’s GRANITE – Phase 2/3 in colorectal
• Multiple peptide/DNA neoantigen vaccines in earlier trials
Personalized cancer vaccines are moving fast.
Very exciting for the field of drug discovery to have more players competing in it.
Even if you disagree with the timeline, having more resources and more brilliant minds in this space will be beneficial long term.
2/2 Second, on the messaging around AI. I do not agree that my messaging has been disproportionately negative. In fact it has been about equally balanced between risks and benefits: I’ve written one major essay about each, and even in interviews where I discuss the risks, I make sure to frequently mention the incredible benefits as well as proposing possible solutions to the risks (short clips from my interviews that end up on social media tend to be disproportionately negative, as that gets clicks). In fact, I wrote Machines of Loving Grace because I didn’t feel the AI industry was painting an inspiring enough picture of how the technology could radically transform the world for the better. The bulk of the essay is devoted to refuting skepticism of AI’s potential in health and biology, and showing why I think it will actually be possible to cure most human disease in ~5-10 years, as crazy as it may sound to ordinary people and frankly to biologists as well (I used to be one!). And, if you read my most recent essay (Policy on the AI Exponential), I discuss concrete proposals for how to streamline the FDA process to make sure the deluge of AI-accelerated drugs isn’t slowed down by the regulatory process. I feel the urgency here: I lost my father to Hepatitis C only a few years before the development of direct-acting antivirals (sofosbuvir), which cure 95% of patients and probably would have cured him.
I do agree that the public has a negative view of AI (and that this is a big problem), but I don’t think it is primarily caused by me or any other AI leader warning about AI’s risks. I think it is fundamentally a crisis of trust. I think that ordinary people don’t trust companies, governments, or the tech industry and always suspect that we are cooking up some new way to screw them over. The causes of this go back decades and AI is just the latest iteration of it. I don’t think that a glitzy marketing campaign with a positive spin (which some have advocated that Anthropic do) is the way to win back that trust — at this point, saying that AI will cure cancer is more a cliche than it is inspiring, and most people think it is deceptive. The thing that will work is *actually curing cancer*. I think by far the most accurate criticism of AI companies including Anthropic is that we haven’t yet delivered on our big promises to benefit the world. That is totally on us, and I think it’s the criticism you should be making, instead of all this stuff about messaging and marketing.
We are however doing our best to fix this: Anthropic is ramping up its efforts very quickly in biology and medicine, and we hope to have incredible results in the coming years and some early glimmers in the coming months. When we’ve actually accomplished something real, the whole world will hear about it, as loudly as possible, you have my word on that. But until then I don’t want to make empty promises, and in the meantime I feel compelled to speak honestly about the very real risks of AI and how to address them. Honesty is the right thing on the merits, and in terms of public credibility and trust it is no worse than, and may in fact be better than, an approach that ignores or distracts from risks which people instinctively understand are real.
For those curious, here are a few specific improvements the US has made recently:
1. Real-world evidence (2025): FDA removed a major barrier to using real-world data in drug/device applications.
2. 10-to-1 deregulation (2025): HHS/FDA began identifying regulations to eliminate, with a goal of removing 10 regulatory actions for every new one.
3. RAPID (2026): FDA + CMS created a pathway to speed Medicare coverage for certain breakthrough medical devices after FDA authorization.
4. Real-time clinical trials (2026): FDA began testing trials where regulators can see safety and efficacy signals as the trial happens, rather than waiting for traditional data reporting.
In case you missed it, here are the latest drugs to become FDA-approved in the past 10 days:
1. Zenbexus (iberdomide) – Aug 13
New oral treatment for multiple myeloma (a blood cancer) after prior therapy
2. Tudriqev – Aug 6
Engineered virus therapy (used with another drug) for advanced melanoma that stopped responding to prior treatment
3. Orzeyful (oveporexton) – Aug 5
First drug that targets the root cause of narcolepsy type 1, helping with sleepiness and muscle weakness
4. mFLUSIVA – Aug 5
First mRNA flu vaccine, approved for adults 50 and older
In data from a new trial, semaglutide slowed the rise of a 25-protein blood signature that predicts future dementia risk in older adults with overweight/obesity and cardiovascular disease (no diabetes). Over 2 years, the predicted 5-year dementia risk increase was 2.5× smaller than placebo (≈26% lower predicted event rate).
Or in simple English:
People taking semaglutide showed a smaller jump in blood markers linked to higher future dementia risk than those not on it.