LLMs

Serving an LLM is usually discussed in pleasantly managerial language: latency, throughput, context windows, GPU memory, quantization, cache eviction. Nice clean nouns. Then the model ruins the spreadsheet by producing internal activations that are thousands of times larger than ordinary values, while some tokens quietly become attention magnets for reasons that are not exactly semantic. Very professional behavior from a trillion-dollar technology stack. ...

Formula discovery sounds like the part of science where artificial intelligence should behave like a heroic mathematician: stare at data, discover a law, and write down a clean equation while everyone else politely applauds. That is the cinematic version. The actual engineering problem is less glamorous and much more useful. Symbolic regression already searches for equations. Given enough variables, operators, constants, and patience, it can produce formulas that fit data. The trouble is that “fits data” and “means something physically” are not the same sentence. In a high-dimensional materials dataset, symbolic regression can wander through a forest of plausible-looking algebra and return a formula that is accurate, ornate, and scientifically suspicious. A spreadsheet can also produce a trendline. We do not usually call that physics. ...

AI has a carbon problem. It also has a paperwork problem. The carbon problem is familiar enough: models require chips, chips require factories, data centers require power, and “cloud” remains one of technology’s more successful euphemisms for buildings full of hot machines. The paperwork problem is quieter. If organizations want to measure environmental impact seriously, they need Life Cycle Assessment, or LCA: the discipline of tracking environmental burdens across extraction, production, use, and end-of-life. That work depends on fragmented studies, sector-specific data, inconsistent terminology, and long technical reports written in the dialect of people who enjoy appendices. ...

Trading teams rarely fail because nobody had a title. They fail because the signal gets lost somewhere between the analyst, the sector specialist, the portfolio manager, and the final trade list. Someone sees momentum. Someone else sees valuation. A news analyst notices a red flag. A macro analyst says the regime is awkward. Then the PM receives a pile of half-compatible opinions and performs the ancient institutional ritual known as “synthesis,” which is often just a polite word for discretionary compression. ...

Planning looks innocent until the planner starts listing every possible thing that could happen. Move this object here. Move that object there. Load this package into that vehicle. Fly this aircraft between those cities. Refuel it at this level. Then do the same for every other object, location, vehicle, person, and intermediate state the model permits. Very quickly, the planner is not solving the business problem. It is drowning in its own imagination. ...

A fire alarm can cause people to evacuate. It can cause a building to enter alert mode. It can trigger emergency procedures, bring firefighters, and make everyone suddenly remember where the stairs are. But does a fire alarm cause a fire? Obviously not. At least, obviously not to a human who understands the causal structure. The alarm is usually an effect or signal of fire risk, not the origin of the fire itself. A model trained on enough sentences of the form “fire alarm causes…” may not be so careful. It may see the familiar phrase pattern, complete the familiar answer, and walk directly into the wrong conclusion with excellent grammar. ...

Conversation is usually treated as the interface layer of AI. The user asks. The model answers. The chatbot smiles politely, perhaps too politely, and everyone pretends that a slightly longer prompt is the same thing as a better thinking system. This is convenient, measurable, and occasionally profitable. It is also probably too shallow. ...

Budget meetings have a useful cruelty. They make vague AI strategy sound ridiculous. A team may begin with the familiar story: the model is not reasoning well enough, so the company needs a larger model, a longer context window, more inference-time search, and probably a procurement conversation involving GPUs. Very modern. Very expensive. Also not always the right diagnosis. ...

Recipe localization looks like an easy prompt. “Create a Jamaican version of Moroccan couscous.” The model smiles politely, throws in jerk seasoning, allspice, scotch bonnet, maybe coconut milk if it is feeling ambitious, and returns something that looks country-specific enough to survive a quick marketing review. The title says “Jamaican.” The ingredients sound Jamaican. The format is clean. No hallucinated oven temperature from another dimension. Excellent, ship it. ...

Logs are useful until they become a landfill. Every serious automation system eventually produces the same awkward artifact: a long trace of what happened. A machine moved here. A sensor changed there. An object collided, rolled, paused, reversed, bounced, touched something else, and then the system reached—or failed to reach—the desired state. In principle, this trace contains the answer. In practice, it is the kind of answer that makes a language model stare at 5,000 tokens of coordinates and politely hallucinate a story. ...