Concern 139 · Working draft · editorial review in progress
Gameable metrics
A gameable metric rewards behavior that improves the measured score without delivering the intended benefit.
Understanding the concern
Developers may optimize for a public benchmark or a service target because it determines rankings or rewards. The system can then become better at the measurement while users see little improvement.
This does not require dishonest intent. A narrow target can guide sincere effort in the wrong direction. Independent evaluations and qualitative review can help test whether gains carry over to real tasks.
An example
A support system closes tickets faster by giving incomplete answers that users must reopen later.
Illustrative unless identified as a documented case.
Words in plain English
- Reward
- A signal used in some training methods to favor certain behavior. A high reward score does not necessarily mean a good result for people.
- Benchmark
- A standard test used to compare systems. It only measures the tasks and conditions included in that test.
Evidence and its limits
Supports proxy optimization and evaluation fragility; the support-service example is illustrative.
Gao, Schulman, and Hilton · ICML 2023 · Research study
Scaling Laws for Reward Model Overoptimization ↗ (opens in a new tab)Examines optimization of an imperfect proxy reward with an experimental reference reward; not a complete model of human values.
Dehghani and colleagues · 2021 · Research analysis
The Benchmark Lottery ↗ (opens in a new tab)Shows how benchmark selection affects research rankings and conclusions.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
When this number improves, do the people using the service actually get a better result?
Keep track of different views, what needs checking, and any next step in your own discussion notes.
Open discussion notes →Principles for the conversation
Before you finish · reflect together
Virtues and principles to consider
Virtues are qualities we practice in how we treat people and make choices. They are not scores for judging someone. Use these ideas to explore what a thoughtful response could look like.
Humility
Humility means recognizing the limits of our knowledge and being willing to learn from others. Expertise can be valuable without answering every question.
State where evidence is weak, invite criticism, and listen to people with different experience. Leave room to revise a decision when new information appears.
Ask together: What might we be missing, and who could help us see it?
Prudence
Prudence means using careful judgment before and during action. It balances worthwhile opportunities with the need to avoid harm that could have been anticipated.
Start with a limited trial, set stopping points, and prefer choices that can be undone when uncertainty is high. Review what happens rather than assuming the original plan remains sound.
Ask together: What is a careful next step, and when should we stop or change course?
Truthfulness
Truthfulness means making claims that match the evidence and being clear about what we do not know. It includes correcting mistakes rather than protecting a polished story.
Check sources, label guesses, and distinguish a trial result from a proven benefit. If AI helped produce a claim, someone still needs to take responsibility for checking it.
Ask together: What can we honestly say, and what still needs checking?
Editorial ratings
These are editorial judgments from the register, not measured probabilities or predictions about your situation.
About the register and scoring →More ways to explore
Search for more writing
For more specific or recent material, open a search below or ask for a web summary. AI-generated summaries can contain mistakes; open the original articles to check them.