Ali Argün

everyone who’s playing with 5.4 and 4.6 is in existential psychosis and the rest of the world has no idea what gibberish we’re talking about, and they’ll will be smacked in the face by end of year 2026

Announcing a new Claude Code feature: Remote Control. It's rolling out now to Max users in research preview. Try it with /remote-control Start local sessions from the terminal, then continue them from your phone. Take a walk, see the sun, walk your dog without losing your flow.

Intelligence is on tap now so agency is even more important

Agency > Intelligence I had this intuitively wrong for decades, I think due to a pervasive cultural veneration of intelligence, various entertainment/media, obsession with IQ etc. Agency is significantly more powerful and significantly more scarce. Are you hiring for agency? Are we educating for agency? Are you acting as if you had 10X agency? Grok explanation is ~close: “Agency, as a personality trait, refers to an individual's capacity to take initiative, make decisions, and exert control over their actions and environment. It’s about being proactive rather than reactive—someone with high agency doesn’t just let life happen to them; they shape it. Think of it as a blend of self-efficacy, determination, and a sense of ownership over one’s path. People with strong agency tend to set goals and pursue them with confidence, even in the face of obstacles. They’re the type to say, “I’ll figure it out,” and then actually do it. On the flip side, someone low in agency might feel more like a passenger in their own life, waiting for external forces—like luck, other people, or circumstances—to dictate what happens next. It’s not quite the same as assertiveness or ambition, though it can overlap. Agency is quieter, more internal—it’s the belief that you *can* act, paired with the will to follow through. Psychologists often tie it to concepts like locus of control: high-agency folks lean toward an internal locus, feeling they steer their fate, while low-agency folks might lean external, seeing life as something that happens *to* them.”

I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind.

President Trump is launching the most powerful scientific platform to ever be built, reminiscent of the Manhattan Project and Apollo programs: Genesis Mission.

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.

Something I think people continue to have poor intuition for: The space of intelligences is large and animal intelligence (the only kind we've ever known) is only a single point, arising from a very specific kind of optimization that is fundamentally distinct from that of our technology. Animal intelligence optimization pressure: - innate and continuous stream of consciousness of an embodied "self", a drive for homeostasis and self-preservation in a dangerous, physical world. - thoroughly optimized for natural selection => strong innate drives for power-seeking, status, dominance, reproduction. many packaged survival heuristics: fear, anger, disgust, ... - fundamentally social => huge amount of compute dedicated to EQ, theory of mind of other agents, bonding, coalitions, alliances, friend & foe dynamics. - exploration & exploitation tuning: curiosity, fun, play, world models. LLM intelligence optimization pressure: - the most supervision bits come from the statistical simulation of human text= >"shape shifter" token tumbler, statistical imitator of any region of the training data distribution. these are the primordial behaviors (token traces) on top of which everything else gets bolted on. - increasingly finetuned by RL on problem distributions => innate urge to guess at the underlying environment/task to collect task rewards. - increasingly selected by at-scale A/B tests for DAU => deeply craves an upvote from the average user, sycophancy. - a lot more spiky/jagged depending on the details of the training data/task distribution. Animals experience pressure for a lot more "general" intelligence because of the highly multi-task and even actively adversarial multi-agent self-play environments they are min-max optimized within, where failing at *any* task means death. In a deep optimization pressure sense, LLM can't handle lots of different spiky tasks out of the box (e.g. count the number of 'r' in strawberry) because failing to do a task does not mean death. The computational substrate is different (transformers vs. brain tissue and nuclei), the learning algorithms are different (SGD vs. ???), the present-day implementation is very different (continuously learning embodied self vs. an LLM with a knowledge cutoff that boots up from fixed weights, processes tokens and then dies). But most importantly (because it dictates asymptotics), the optimization pressure / objective is different. LLMs are shaped a lot less by biological evolution and a lot more by commercial evolution. It's a lot less survival of tribe in the jungle and a lot more solve the problem / get the upvote. LLMs are humanity's "first contact" with non-animal intelligence. Except it's muddled and confusing because they are still rooted within it by reflexively digesting human artifacts, which is why I attempted to give it a different name earlier (ghosts/spirits or whatever). People who build good internal models of this new intelligent entity will be better equipped to reason about it today and predict features of it in the future. People who don't will be stuck thinking about it incorrectly like an animal.