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 From these experiments, uploaded the unpublished figure below and asked GPT-5 Pro to explain it.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.

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!

GPT-5 is here. Rolling out to everyone starting today.

LIVE5TREAM THURSDAY 10AM PT

LIVE5TREAM THURSDAY 10AM PT

This week, ChatGPT is on track to reach 700M weekly active users — up from 500M at the end of March and 4× since last year. Every day, people and teams are learning, creating, and solving harder problems. Big week ahead. Grateful to the team for making ChatGPT more useful and delivering on our mission so everyone can benefit from AI.