Image created with Flux Pro v1.1 Ultra. Image prompt: CU Boulder brand style — CU Gold & Black, Helvetica Neue, Flatirons, Tuscan-vernacular sandstone + red-tile roofs; chemistry lab bench, bright even light, close-up perspective, buffalo silhouette watermark; integrate the category “Science” via Prop: microscope and glassware with a small desk card “SCIENCE”; natural light, clean professional inspiring tone, crisp focus, subtle grain, editorial composition
Here’s the thing: For 35 years, I’ve researched the immune system & have been fortunate to make many important, impactful discoveries, placing me in the top 0.5% of immunology experts.
The
@OpenAI
GPT-5 Thinking & Pro models now match or even surpass my expertise in immunology!
GPT-4o was below the level of medical professionals on medical reasoning benchmarks GPT-5 (apparently Thinking medium) now far exceeds them. (Usual benchmark caveats apply) https://x.com/emollick/status/1955381296743715241
GPT-5 (with high reasoning effort) achieves near-perfect accuracy on a high-quality ophthalmology question-answering dataset. Based on these other reports, GPT-5 seems to be a very strong model at medical reasoning. https://x.com/omarsar0/status/1956003145349521780
My “Move 37” Moment with GPT-5
Today, I’m sharing one of my most remarkable experiences testing the GPT-5 Thinking and Pro models.
In our lab, about 2 years ago we conducted a series of cutting-edge immunology experiments designed to manipulate the energy metabolism of T cells, immune cells with the power to impact cancer immunotherapy, chronic diseases, and autoimmunity.
We obtained fascinating results, but one finding remained unexplained. Weeks of work led us to a partial explanation, yet the full picture remained elusive.
From these experiments, uploaded the unpublished figure below and asked GPT-5 Pro to explain it.
GPT-5:
✅ Correctly identified our key findings from the figure alone (though other models also could do this).
✅ Proposed the exact experiment we later performed, something that had taken us weeks to design (o3-pro also had suggested this).
✅ Most remarkably suggested a mechanism that finally explained these results!
For me this was equivalent to AlphaGo’s legendary Move 37.
It showed that AI has become top expert and true scientific collaborator, capable of true insight.
While these results have not yet been published, I am sharing some of GPT-5’s output as an example for other scientists and to show how dramatically this will accelerate science! I will also be writing and submitting this paper, and will need to acknowledge GPT-5’s contributions in it!
—
From GPT-5
What the data say:
•Brief 2DG exposure at the first activation imprints a long‑lasting shift toward a CCR6+ and CD161+ phenotype with increased IL‑17A competency that is still evident two weeks later at reactivation.
•It is dose responsive. From none → 3 mM 2DG, CCR6+ cells rise from ~0.7% to ~12% and CD161+ cells from ~1% to ~21%. IL‑17A+ cells increase from ~0.3% to ~4% overall, with the IL‑17A signal concentrated in the CCR6+ and CD161+ compartments.
•Low glucose alone (0.5 mM) does not reproduce the effect. That argues against simple glucose deprivation or reduced glycolytic flux as the driver.
•The enrichment for CD161 is stronger than for CCR6, which often tracks with Th17‑like or mucosal/innate‑like CD4 programs.
High‑level interpretation:
1. 2DG is programming, not just acutely inhibiting. A short exposure during priming leaves a durable memory of “stress” that biases the lineage toward Th17‑like traits.
2. Mechanism is unlikely to be only glycolysis blockade. The low‑glucose control is weak, which pushes the mechanism toward 2DG’s effects on protein glycosylation and cytokine receptor biology.
3. Top mechanistic hypothesis. 2DG partially blocks N‑linked glycosylation of IL‑2Rα and other glycoproteins at priming, reducing IL‑2–STAT5 signaling, which normally suppresses Th17. Reduced IL‑2 tone at that window would lift the brake on a CCR6+ CD161+ IL‑17‑competent program that persists after washout.
4.Alternative or complementary hypothesis. 2DG selects for pre‑existing CCR6+ or CD161+ clones that rely less on glycolysis, rather than de novo differentiation. The end result is the same phenotype, but the lever is selective survival or proliferation.
5. A carefully timed 2DG “pulse” could be a simple knob to enrich a Th17‑like helper subset with better persistence potential and mucosal‑homing traits.
Prioritize these:
+D‑mannose with 2DG to restore N‑glycosylation. Loss of the CCR6/CD161/IL‑17A phenotype with mannose would implicate glycosylation.
+Methyl‑pyruvate or acetate to bypass glycolytic ATP/pyruvate deficits. Rescue here would implicate energy metabolism.
Compare 2DG with tunicamycin (glycosylation inhibitor) and with glycolysis‑only inhibitors that do not hit glycosylation (iodoacetate, PFKFB3 inhibitor). Match exposure windows & doses
Surface CD25 maturation and glyco‑shift (PNGase F or Endo H blot on IL‑2Rα).
pSTAT5 after an IL‑2 pulse at 24–48 h of priming with or without 2DG.
Phenocopy with IL‑2 neutralization or low‑dose JAK3 inhibition. Counter‑rescue with high IL‑2 or an IL‑2 mutein.
https://x.com/DeryaTR_/status/1954354352648225235
RT @deedydas: Huge computer science result: A Tsinghua professor JUST discovered the fastest shortest path algorithm for graphs in 40yrs.…”” / X https://x.com/algo_diver/status/1954423622787039379
This guy literally built a viral website from scratch in 10 minutes with GPT-5 https://x.com/aaditsh/status/1954210152170893668
Palletizing in the real world! 📦🤖 How do you stack 65 unique SKUs on a pallet when they arrive in random order? Here’s how an on-the-fly algorithm solved it in a real logistics use case with only a single-digit buffer. Every placement was checked for stability, not just for https://x.com/IlirAliu_/status/1955323367059575263
Another example of a persistent problem with LLMs. They do very well on standard medical questions, but when the right answer is replaced with “none of the above” performance drops. More recent models generally have lower drops in performance. https://x.com/emollick/status/1955296575674056992
Artificial Analysis on X: “GPT-5 occupies both the #1 and #2 positions in our long context reasoning benchmark (AA-LCR) 🤯 AA-LCR tests long context performance through testing reasoning capabilities across multiple long documents (~100k tokens). Questions typically require considering multiple documents https://t.co/BEq9ZspRMs” / X
https://x.com/ArtificialAnlys/status/1953523986526351576
Bartosz Naskręcki on X: “Ok, some general comments while I am waiting for the other tasks. GPT 5 and GPT 5 Thinking are nothing very novel for research mathematicians compared to o3-pro and o4-mini-high. But GPT 5 Pro is different. It uses much more compute and the quality of the answers is superb.” / X
https://x.com/nasqret/status/1953566692686397885
Matthew Berman on X: “Vibe coding a full Excel clone step-by-step with GPT-5 is kinda nuts. (I know I’m still far from a full clone, but this is after about 45 minutes of work) https://t.co/upr5QSmluJ” / X
https://x.com/MatthewBerman/status/1954694677736956297
GPT-5 has been hovering around a 7% diff edit failure rate since its release to Cline last Thursday. How have you liked GPT-5 so far in Cline? https://x.com/cline/status/1955357460627329151
GPT-5 is live in Cline. We’ve been working with OpenAI to get this model ready, and here’s our take: it’s disciplined, persistent, & highly competent. It’s collaborative in planning & and a diligent operator while acting. It plans thoroughly, asks optioned follow-ups when https://x.com/cline/status/1953525433808695319
GPT-5 is speed-running Pokemon It’s 3x faster than o3 https://x.com/scaling01/status/1955813023735828587
gpt-5 is the best coding model in the world and is now the default in @cursor_ai. https://x.com/gdb/status/1953521501548032512
GPT-5 Just Finished Pokemon Red! : r/singularity https://www.reddit.com/r/singularity/comments/1mq2irv/gpt5_just_finished_pokemon_red/
GPT-5 just finished Pokémon Red! 6,470 steps vs. 18,184 for o3! Check the stats site to compare! That’s a huge improvement! Well done, @OpenAI you cooked with GPT-5. What an incredible model. Next up: GPT-5 vs. Pokémon Crystal (16 Badges + Red). The run starts soon on Twitch. https://x.com/Clad3815/status/1955980772575268897
GPT-5 now rolled out to 20% of paid users and doing >2B TPM on the API! so far so good… excellent work by the eng and infra teams!”” / X https://x.com/sama/status/1953563605733118317
gpt-5 is SOTA on FrontierMath:”” / X https://x.com/gdb/status/1953710811957858404
In short 49th to 98th percentile of performance in IOI in one year without training any specialised models. Same RL as for everything else we do”” / X https://x.com/MillionInt/status/1954977818128888311
1/n I’m thrilled to share that our @OpenAI reasoning system scored high enough to achieve gold 🥇🥇 in one of the world’s top programming competitions – the 2025 International Olympiad in Informatics (IOI) – placing first among AI participants! 👨💻👨💻 https://x.com/SherylHsu02/status/1954966109851119921
Announcing gold medal-level performance (#6 relative to humans; #1 relative to AIs) on this year’s International Olympiad on Informatics (IOI). Achieved with an AI reasoning system, without IOI specific training!”” / X https://x.com/gdb/status/1954984230343282808
In my opinion, the most important takeaway from this result is that our @OpenAI International Math Olympiad (IMO) gold model is also our best competitive coding model. 🧵”” / X https://x.com/polynoamial/status/1954966398989635668
Multiple AI systems won gold medals at the 2025 International Mathematical Olympiad (IMO). Exciting as that sounds, @GregHBurnham argues that it represents little progress: an unlucky draw of problems made the event relatively uninformative. Is that cope? Judge for yourself. 🧵 https://x.com/EpochAIResearch/status/1953567563557838920
How Google and NASA are Testing AI for Medical Care in Space | Google Cloud Blog https://cloud.google.com/blog/topics/public-sector/how-google-and-nasa-are-testing-ai-for-medical-care-in-space
🏆 We’re thrilled to announce that Meta FAIR’s Brain & AI team won 1st place at the prestigious Algonauts 2025 brain modeling competition. Their 1B parameter model, TRIBE (Trimodal Brain Encoder), is the first deep neural network trained to predict brain responses to stimuli https://x.com/AIatMeta/status/1954865388749205984
[2507.22229] TRIBE: TRImodal Brain Encoder for whole-brain fMRI response prediction https://www.arxiv.org/abs/2507.22229
Let’s take a look into GPT-5’s record-setting performance on FrontierMath. How did it perform on the holdout vs. non-holdout set, how did it do across tiers, and what new Tier 4 problems did it solve? 🧵 https://x.com/EpochAIResearch/status/1955667249252978741
My “Move 37” Moment with GPT-5 Today, I’m sharing one of my most remarkable experiences testing the GPT-5 Thinking and Pro models. In our lab, about 2 years ago we conducted a series of cutting-edge immunology experiments designed to manipulate the energy metabolism of T https://x.com/DeryaTR_/status/1954354352648225235
We’ve scored highly enough to achieve gold at this year’s IOI online competition with a reasoning system — placing #6 when ranked with humans and #1 when ranked with other AIs. In just a few weeks: • 2nd at AtCoder • Gold medal-level at IMO • Gold medal-level at IOI”” / X https://x.com/OpenAI/status/1954969035713687975
KAIST Develops AI That Automatically Designs Optimal Drug Candidates for Cancer-Targeting Mutations https://www.alphagalileo.org/en-gb/Item-Display/ItemId/261880?returnurl=https://www.alphagalileo.org/en-gb/Item-Display/ItemId/261880
Using generative AI, researchers design compounds that can kill drug-resistant bacteria | MIT News | Massachusetts Institute of Technology https://news.mit.edu/2025/using-generative-ai-researchers-design-compounds-kill-drug-resistant-bacteria-0814
Watching the model solve these IMO problems and achieve gold-level performance was magical. A few thoughts 🧵”” / X https://x.com/SherylHsu02/status/1946478334013321231
