Today I am unveiling the second remarkable breakthrough with the OpenAI GPT-5 thinking model. We had carried out an extraordinarily complex, month-long experiment to develop engineered cells against lymphomas. I asked GPT-5 to predict the full sequence & outcome of this experiment. The result was nothing short of staggering: it foresaw most of the experimental results with uncanny accuracy & even proposed refinements & optimizations we should implement! This is the dawn of in silico experimentation, where we can simulate months or even years of laboratory work in advance, compressing the scientific timeline from years to weeks! This changes everything about how science is done, ushering in an era where discovery moves at the speed of thought! —- Prompt: predict, in high detail, the outcomes of the following experiment: •Human CD8⁺ memory T cells are engineered to express an anti-CD19 CAR. Approximately 90% of these cells also contain a Tet-inducible CD19 antigen construct that remains off unless doxycycline is added. •Day 0: CAR T cells are mixed with CD19⁺ lymphoma cells. •Day 2: Doxycycline is added to the culture to induce CD19 expression in the engineered T cells. •Readouts: Cell survival, activation markers, and proliferation are measured 2 days, 7 days, and 14 days after doxycycline addition. ————- GPT 5 (continued from the screenshots): •Induced CD19 density and doxycycline dose: High density drives lethal fratricide and a steep crash by Day 4. Lower density can act like an antigen feeder to expand CAR T cells without catastrophic loss. •Initial E:T: High E:T clears tumor pre-doxycycline and protects function. Low E:T lets tumor persist into the fratricide window, which amplifies activation and death. •Fraction of inducible cells: The 10% antigen-negative fraction forms the seed for long-term persistence and response on re-challenge. •Cis sequestration strength: Strong cis binding dampens both fratricide and responsiveness to external tumor at re-challenge. Weak cis allows more killing of both self and tumor. Readouts to confirm or falsify: 1. Differential survival by genotype: Track CAR+ CD19-inducible+ versus CAR+ inducible- cells separately with barcodes or reporters. Expect selective loss of the inducible+ cohort by Day 4-7 2. Apoptosis kinetics: Annexin V and active caspase 3 peaks within 24 to 48 hours after doxycycline, concentrated in the inducible+ cohort. 3. Activation and exhaustion panels: CD69, CD25, 4-1BB, HLA-DR, then PD-1, TIM-3, LAG-3, TIGIT, TOX, and TCF-1 over time to show the Day 4 spike and the Day 7 to 14 remodeling. 4. Function per cell: Short coculture killing assays normalized by T-cell number. Per-cell cytotoxicity remains strong at Day 7 and 14 in survivors. 5. Cis versus trans evidence: Co-immunoprecipitation or proximity assays for CAR bound to same-cell CD19, and imaging synapse assays to quantify T-T killing. 6. Cytokine fields: IFN-γ, TNF, IL-2, GM-CSF peaking at Day 4, lower on later re-challenges. Practical predictions in numbers, to calibrate expectations: These are typical ranges if doxycycline induces high CD19 density and E:T started at 1:1 to 1:2. Adjust upward or downward based on your exact settings. •Tumor viability: Day 2 pre-doxycycline: 10 to 30% remaining. Day 4: 0 to 10% if mostly cleared earlier, or 20 to 40% if E:T was low and T-cell crash occurred. Controls and variants that de-risk interpretation: •No-doxycycline control to isolate tumor-only dynamics and basal CAR function. •CAR-negative but inducible-CD19 positive T cells to measure bystander fratricide requirement for CAR. •Doxycycline titration to define the safe antigen density window that expands cells without catastrophic fratricide. •Washout of doxycycline at 24 to 48 hours to test reversibility of fratricide and rescue of function. •CRISPR disruption of CD19 cytoplasmic tail in the inducible construct to alter synapse stability and test cis signaling contributions.