# What Sapolsky's first lecture means for LLMs and decision models (slim) > Vlad Cealicu reads the first lecture of Robert Sapolsky's Human Behavioral Biology course as a guide to decision models. The answer nobody wrote, what a threshold does to a probability, the buckets behind a model's answer, 17 of the 26 decision models we list sharing Qwen ancestry, and why a model is the case where the experiment can be run. - Full: https://www.anchorterminal.com/blog/sapolsky-first-lecture-decision-models.md (~4,600 tokens) · this version ~2,080 tokens · JSON https://www.anchorterminal.com/blog/sapolsky-first-lecture-decision-models.json · canonical https://www.anchorterminal.com/blog/sapolsky-first-lecture-decision-models - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10 - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) By Vlad Cealicu, 10 November 2026. 2,096 words, about 9 min to read. - 26: decision models we list - 17: of them with at least one model built on a Qwen base - 60%: how often two models that were both wrong had picked the same wrong answer, against 33% by chance Decision models in the directory on 10 November 2026, and how alike models are when they're wrong. Robert Sapolsky starts his Stanford course on human behavioural biology with a multiple-choice question. I read that as a decision request, because it has a state, a question and a fixed list of answers, which is what an agent sends a [decision model](/categories/decision-models), a model that gives back a probability for each answer you allowed and no text [[3]](#ref-3). The third answer is only on Sapolsky's list because somebody found the gene. The fix is one more answer on the list, none of these, and then watching how much probability lands on it over a week, because that number tells you how much of what's coming in your list doesn't cover. ## What we do to the number Sapolsky's first big point is that thinking in categories does three things to you. I think a decision model is better at this than we are, because it gives you 0.51 and we're the ones who write the next line. With the first one, 0.51 and 0.99 go down the same branch and 0.49 and 0.51 go down different ones, which is his first two problems in one line of Go. The number has to mean something for that to work, and that's calibration, whether the things a model gives 0.9 come true about nine times in ten. His third problem is the whole picture, and for an agent the whole picture is the chain, because an agent makes one decision after another and what you care about is whether the whole run comes out right. Chance that every decision in a chain is right when each is right 95% of the time, in per cent | Decisions in a row | All right | | --- | --- | | 1 | 95 | | 5 | 77 | | 10 | 60 | | 20 | 36 | | 50 | 8 | Each series has a zero-based scale. Sapolsky gives the students James Gleick's Chaos to read, for the argument that taking a thing apart and putting it back together is how you fix a clock, and a behaviour is closer to a cloud [[2]](#ref-2). ## Why did it say yes? His second idea is the buckets. Why a decision model said yes, going back in time 1. **The second before** (you can test it). The question, its wording and the order of the answers 2. **Just before that** (you can test it). The state the agent passed in, and what it left out 3. **The hours before** (you can test it). How busy the server was, which can change the answer to the same request 4. **Before it was released** (on the card, if they say). The fine-tune, which decisions it was trained on and who labelled them 5. **Before that** (on the card, if they say). The base model, and 17 of the 26 we list have one built on Qwen 6. **Long before** (hard to see from outside). What the base model's makers were training it to be good at I think this is where it gets better than biology, because a biologist can't run the man again with one hormone changed, and we can send the same request 500 times, shuffle the answers, change one line of the state, and for the open ones put the same training on a different base and compare. The first bucket is already measured. The base model is the bucket I'd look at first. ## Two quotes he reads out Sapolsky reads out lines from three of the most influential scientists of the last century, as he puts it, each of them explaining behaviour from inside one bucket, and two of the three have a version in this market. The first is John Watson, who founded behaviourism and said that given a child at birth and control of how it was raised he could make it into anything, a doctor, a lawyer, a beggar or a thief. The second is Egas Moniz, who invented the lobotomy and, in the line Sapolsky reads, had seen "cures and improvements but no failures" [[2]](#ref-2). - [Kev](https://www.anchorterminal.com/tools/jaredpalmer-kev.md), B. release notes that list what it does badly, option order among them - [Strands Decider 2B](https://www.anchorterminal.com/tools/strands-decider.md), C. measured figures for each limitation - [Jev](https://www.anchorterminal.com/tools/typesafe-jev.md), C. a known-limitations page Three that publish where they fail ## Does a model decide? Sapolsky also asks the hall for a show of hands on a list of beliefs, and free will is on it [[2]](#ref-2). If the man's case came in as a ticket today, with the two answers most of us would have written, I'd want a none-of-these answer so the model has somewhere to put the disease nobody listed, the number kept as a number until the last step, and a second opinion from a model that isn't a relative of the first. We haven't run any of this ourselves. --- More in [Opinion](https://www.anchorterminal.com/blog/opinion/index.md) · Older opinion [Just in time society](https://www.anchorterminal.com/blog/just-in-time-society.md) - Older: [A machine that builds the benchmark](https://www.anchorterminal.com/blog/a-machine-that-builds-the-benchmark.md) - Newer: [Google made four TPUs this year, and the rest of us get an interest form](https://www.anchorterminal.com/blog/google-tpu-8-four-chips-and-an-interest-form.md) - All posts: https://www.anchorterminal.com/blog/index.md Anchor Terminal grades the tools AI agents run on, with a source for every score. ## References Read on 10 November 2026. The lecture details are from the transcript of the 2010 recording, and the 2024 recording may differ from it in small ways. [1] Stanford School of Humanities and Sciences, "1. Human Behavioral Biology, Introduction by Robert Sapolsky", a spring 2024 lecture posted on 12 March 2026. The lecture this post is about. [2] The Singju Post, full transcript of Robert Sapolsky's introduction to Human Behavioral Biology, recorded at Stanford on 29 March 2010. Source for the opening case and its three explanations, the three problems with thinking in categories and the exam scores of 65 and 66, the buckets, the lines from John Watson and Egas Moniz and what Sapolsky says of each, the show of hands on free will, and James Gleick's Chaos with the clock and the cloud. [3] Anchor Terminal, decision model listings and the category page, 10 November 2026. Source for what a decision model is, the 26 listings, the test for the category and that it hasn't run, the 17 with a model on a Qwen base (Clef, Decider, Decision 3.0, Drex Max, Drex 1.5 by way of Xiaomi's MiMo distil, elephant-1, GLiClass, JEV-27B-VL, joey-1, Kev, mammoth-1, Microsoft-Decision-1, pplx-decider, pplx-decider-flash, SPEV, Strands Decider and Vela), Decider's and Strands Decider's Qwen and Gemma bases, Drex Max's card naming its base until 30 October, Kev's release notes and its permute endpoint, kettei's abstain policy, Laya's note on over-confident checkpoints, the seven listings that note no limitations section (Drex Max, elephant-1, GLiClass, joey-1, Liquid d1, mammoth-1 and ScaleDown), and the limitations published by Kev, Strands Decider and Jev. [4] Chuan Guo, Geoff Pleiss, Yu Sun and Kilian Q. [5] Anchor Terminal, the Agent Tool Benchmark, methodology 0.7. Source for Performance and Task success being pending in this run, with no score and nothing added to the total. [6] Pouya Pezeshkpour and Estevam Hruschka, August 2023, "Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions", later in Findings of NAACL 2024. Source for a performance gap of approximately 13% to 75% across benchmarks when the answer options are reordered. [7] Elliot Myunghoon Kim, Avi Garg, Kenny Peng and Nikhil Garg, 2025, "Correlated Errors in Large Language Models", Proceedings of the 42nd International Conference on Machine Learning. [8] The Nobel Foundation, Egas Moniz, facts. [9] Wikipedia, "Determined, A Science of Life Without Free Will".