Alex Rubinsteyn
banner
alexr.bsky.social
Alex Rubinsteyn
@alexr.bsky.social
personalized cancer immunotherapy = genomics + immunology + machine learning + oncology

(pirl.unc.edu)
I can’t believe we’re speedrunning super-human automated intelligence with offline BPE tokenization

Like…I was sure something better would win.
February 8, 2026 at 7:05 PM
codex-5.3 caught a totally ruinous copy/paste error in a data download script I wrote by hand before handing off the data to codex-5.2 for simple visualizations

Ran codex-5.3 on a few other repos and it caught small legitimate bugs in each of them. Uh, definitely an improvement
February 6, 2026 at 7:11 PM
February 5, 2026 at 6:28 PM
Reposted by Alex Rubinsteyn
Our latest research showing PRAME as a previously unrecognized therapeutic target in NUT carcinoma just dropped on JITC. Huge thanks to @sitcancer.bsky.social @benjamingvincent.bsky.social @alexr.bsky.social @unclineberger.bsky.social and so may others!!!

jitc.bmj.com/content/14/2...
Shared PRAME epitopes are T-cell targets in NUT carcinoma
Background NUT carcinoma is a rare but highly lethal solid tumor without an effective standard of care. NUT carcinoma is caused by bromodomain-containing NUTM1 fusion oncogenes, most commonly BRD4::NU...
jitc.bmj.com
February 5, 2026 at 1:54 PM
Finally published!

“Shared PRAME epitopes are T-­ cell
targets in NUT carcinoma”

We stumbled into working on a rare deadly cancer without effective treatments and found that some existing TCR therapies might be worth trying (at least work in vitro)

Link: jitc.bmj.com/content/14/2...
Shared PRAME epitopes are T-cell targets in NUT carcinoma
Background NUT carcinoma is a rare but highly lethal solid tumor without an effective standard of care. NUT carcinoma is caused by bromodomain-containing NUTM1 fusion oncogenes, most commonly BRD4::NU...
jitc.bmj.com
February 5, 2026 at 3:02 PM
Ran into a third friend at this Durham co-working space, laptop also full of coding agents running in parallel (four Codex instances)

Three for three now -- split between Claude Code, Cursor, and Codex, I guess I'm the 4th (with 5 Codexes waiting for my attention)
February 2, 2026 at 7:26 PM
New PIRL blog post by @benjamingvincent.bsky.social:

Some advice to companies and clinics starting personalized neoantigen vaccine programs

Link: pirlblog.substack.com/p/some-advic...
Some advice to companies and clinics starting personalized neoantigen vaccine programs
The problems aren't all solved yet...
pirlblog.substack.com
February 2, 2026 at 7:25 PM
Teaching my kids to sing “Costco! Costco!” over the Dsinghis Khan song

(final humiliation of the Cold War)
February 2, 2026 at 2:26 PM
Disturbance in the force…

Sonnet 4.5 Thinking with search just gave me 6 made up paper links in a row (link either didn’t work or went to different unrelated paper)

Feels like it’s been a while (had to go back to ChatGPT)
February 1, 2026 at 3:51 AM
Reposted by Alex Rubinsteyn
Read 1000 moltbook posts and then go back to reading bluesky without going insane challenge
January 30, 2026 at 8:20 PM
Been reading Accelerando just to find out what happens next
January 30, 2026 at 6:11 PM
Raising low tech kids is starting to feel transgressive

(asked about laptop time at a school tour and felt like a fundamentalist)
January 28, 2026 at 2:48 AM
Reposted by Alex Rubinsteyn
January 27, 2026 at 9:37 PM
Claude Code did like 95% of the MHCflurry TensorFlow to PyTorch port in about a day but there are some persistent numerical differences/bugs that it's been churning for a week, playing trial-and-error whack-a-mole coding like a junior dev.

Codex seems to be one-shotting the fix
January 27, 2026 at 6:06 AM
Codex and Claude Code working on the same branch. What could go wrong?
January 27, 2026 at 3:55 AM
Reposted by Alex Rubinsteyn
Ever wondered what happens if you remove Tfh cells from established germinal centres?
January 26, 2026 at 2:20 AM
No one is driving in my neighborhood, the streets have been completely conquered by bands of elementary school aged children with sleds.
Feels like society’s really broken down in the US in a way that’s deeply traumatic.

But also there are college students knocking on doors asking for shovels (they’re not well-prepared) and helping trapped motorists by shoveling and pushing out cars. Up to 24 of them now, wandering streets together
January 25, 2026 at 9:57 PM
the kids are in control
January 25, 2026 at 6:36 PM
I’ve been blocked on an essay about curing cancer with AI forever & realized I couldn’t finish it because I was transitioning from skeptic to believer. Too much dissonance to reach a conclusion.

(reaching a synthesis just as icepocalypse comes to Durham)
January 24, 2026 at 4:43 PM
Hosted some high school students (!) at the UNC Comp Med program who are taking a winter elective on AlphaFold and computational protein modeling (!!)

What a crazy time to be a nerdy kid, everything going exponential all around you while traditional barriers erode and collapse
January 24, 2026 at 12:45 AM
Anti-FAP CAR T cells produced in vivo reduce fibrosis and restore liver homeostasis in metabolic dysfunction–associated steatohepatitis

www.science.org/doi/10.1126/...

(Capstan style aCD5 tLNP delivery of CAR construct to T-cells)
Anti-FAP CAR T cells produced in vivo reduce fibrosis and restore liver homeostasis in metabolic dysfunction–associated steatohepatitis
CAR T cells generated in vivo by T cell–targeted mRNA-LNP delivery eliminated scar-forming cells and ameliorated fibrosis in steatotic liver disease.
www.science.org
January 22, 2026 at 4:03 AM
Raleigh/Durham meteorology nerds: how long am I going to lose power for?
January 22, 2026 at 12:27 AM
what else besides neoantigen vaccines, neoantigen TCR-T, personalized phage therapies, and ASOs for nanorare germline disorders is in the protoplasmic soup from which generative medicine will emerge?
January 21, 2026 at 1:37 AM