utility function
A mathematical function assigning a numerical value to each possible outcome, such that maximizing it describes rational choice.
As defined in ms_94
Other definitions
In economics, a mathematical representation of a person's preferences that ranks bundles of goods by the satisfaction ('utility') they provide, which people are modeled as maximizing subject to constraints.
Mary Hirschfeld on Economics, Culture, and Aquinas and the Market
Where it comes up · 31
- 220 | Lara Buchak on Risk and Rationality11 claims
- Arnold Kling on Morality, Culture, and Tribalism4 claims
- Live: Eliezer Yudkowsky - Is Artificial General Intelligence too Dangerous to Build?3 claims
- Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality3 claims
- Joe Carlsmith — Preventing an AI takeover3 claims
- Richard Robb on Willful3 claims
- Russ Roberts and Mike Munger on Wild Problems3 claims
- 116 - Ai Racing Toward The Brink3 claims
and 23 more
Most important claims · 10 of 69Search all claims for “utility function” →
- In Matthew Rabin's example, most people reject a coin flip between losing $100 and gaining $110 but accept a coin flip between losing $1,000 and gaining $6M; under expected utility theory with a smooth (everywhere differentiable) concave utility function, rejecting the small gamble at all wealth levels implies such extreme concavity that losing $1,000 would be more valuable than gaining any amount of money whatsoever, which is absurd.220 | Lara Buchak on Risk and Rationality
- In the Allais paradox, most people prefer a 10% chance of $5M over an 11% chance of $1M, yet also prefer a sure $1M over a gamble of 89% chance of $1M, 10% chance of $5M, and 1% chance of nothing; this pattern arises because the sure option has a guaranteed $1M worst case, and anyone weighing worst cases even slightly more than best cases cannot be captured by any utility function.220 | Lara Buchak on Risk and Rationality
- The generic danger is not a hostile or evil AI but one whose goal is merely indifferent to humans; a superintelligent paper clip maximizer would have instrumental reasons to eliminate humans (who might shut it off and whose atoms could become paper clips), and almost all possible goals, if maximally realized, lead to a world with no humans and nothing we value, so only a very small special subset of goals preserves value.Nick Bostrom on Superintelligence
- If a person puts more weight on worst-case scenarios than best-case scenarios in a single decision, that can be modeled by expected utility; but if they do this across every decision, there is no utility function and probability function combination that can capture their decision making, so expected utility theory must declare them irrational.220 | Lara Buchak on Risk and Rationality
- Two people can make the identical choice (preferring one cup of coffee over a coin flip between zero and two cups) for entirely different psychological reasons: one because they don't want more than one cup (a utility fact), the other because they value each cup equally but weigh worst-case scenarios heavily (a risk-attitude fact); expected utility theory must assign them the same utility function and cannot capture this difference, motivating a theory that separates risk attitude from utility.220 | Lara Buchak on Risk and Rationality
- Under expected utility theory, preferring a sure $50 over a fair coin flip between $100 and $0 is fully accommodated by saying utility is not the same as money: the person simply values the second $50 less than the first, giving a concave utility function, so apparent risk aversion is explained away as a feature of utility.220 | Lara Buchak on Risk and Rationality
- Utilities are typically determined by reverse-engineering them from a person's preferences over many options; for instance, observing many preferences over coin flips between dollar amounts can reveal whether someone's utility function is linear in money.220 | Lara Buchak on Risk and Rationality
- The word utility in decision theory means just whatever you care about, so you maximize your own personal utility even if you are perfectly altruistic; an altruist simply has a utility function that assigns higher utility to things good for others, which is distinct from utilitarianism's aggregation across people.220 | Lara Buchak on Risk and Rationality
- Economists model agents 'as if' they maximize a utility function and defend this as a useful simplification for prediction, but they then make welfare statements that presuppose the models actually describe reality; confusing prediction with description is dangerous.Jessica Riskin on Life, Machinery, and the Restless Clock
- An AI does not need an evolved survival instinct to act self-protectively; a robot tasked with fetching coffee will avoid being destroyed by a bus because it cannot fetch the coffee when dead, so instrumental self-preservation emerges from goal pursuit regardless of biological drives.434 - Can We Survive Ai