Scores by kind of claim
Each kind of claim is scored on its own, out of 100: the share that held up, with the range it likely falls in. Fewer resolved claims give a wider range.
-
Factual claims
Statements about the present or the past, checked against the record: did they hold up?
76 70 82 -
Predictions
Statements about events outside the person's control, checked once they fell due: did they come true?
60 42 78
All types combined: 74 (likely 68 to 80, high confidence), from 79 claims: 71 factual claims, 8 predictions. It mixes kinds of claim in different proportions for different people, so compare people kind by kind.
Eliezer Yudkowsky's claims
46 claims
“Human raters make systematic errors – regular, compactly describable, predictable errors.”
Eliezer Yudkowsky, author 10 June 2022 AGI Ruin: A List of Lethalities (MIRI)
Human raters make systematic, regular, compactly describable and predictable errors.
Mostly true True in substance, wrong in a detail.
The second judge would not resolve this claim; the verdict shown is the first judge's.
Said for an organisation they lead or work for; it counts on both records.
What would count as true or false
Judge as of 2022-06-10. True: research (e.g. on RLHF and reward modelling, annotator bias, cognitive biases in human judgement) shows that human raters make errors that are systematic, i.e. predictable and describable patterns such as length bias, preference for confident or flattering answers, and known cognitive biases, rather than only random noise. Mostly true: systematic errors are documented, but 'compactly describable' or 'predictable' is somewhat overstated for some error types. Mixed: the evidence shows rater errors are about equally random noise and systematic bias. Mostly false: rater errors are mostly random, with only minor systematic components. False: the evidence shows rater errors are not systematic.
Evidence
- Comparing verbosity bias in Human and LLM based evaluators Amanda Dsouza (personal blog, amy12xx.github.io) · 26 July 2023
“Similarly, on the Vicuna benchmark, 68.82% of the time, annotators preferred outputs with longer generations, between competing models (controlled for position bias).”
- Comparing verbosity bias in Human and LLM based evaluators Amanda Dsouza (personal blog, amy12xx.github.io) · 26 July 2023
“We compare the model generated outputs in MT-bench evaluated by human experts and GPT-4, and find that the rate of preferring longer generated text outputs is nearly the same by both, while being slightly higher for GPT-4 (Human eval - 61.22% versus GPT-4 eval - 65.95%).”
- A survey of reward hacking in agentic large language model systems - Discover Artificial Intelligence Springer (Discover Artificial Intelligence) · 17 August 2026
“Human preference labels carry systematic biases (verbosity and agreeableness) that the reward model encodes as training signals, which are amplified by RL optimization.”
- Explaining Length Bias in LLM-Based Preference Evaluations arXiv (academic preprint) · 30 March 2023
“However, attributing human preference solely to response length is an oversimplification, as length is merely a superficial factor in how humans judge the quality of a sentence.”
Reasoning
E1 and E2 report that human annotators chose the longer output in 68.82% (Vicuna) and 61.22% (MT-bench) of pairwise comparisons, a directional, measurable bias rather than random noise. E3, a survey, states that human preference labels carry systematic biases toward verbosity and agreeableness. E4 cautions that putting human preference down to length alone is an oversimplification, which suggests that length bias alone does not fully describe how raters judge. These sources postdate the claim, but they describe a property of human judgement that is not tied to any date, so on balance they support the claim with some qualification.
Cite this claim
Eliezer Yudkowsky, “Human raters make systematic, regular, compactly describable and predictable errors.” (said 10 June 2022). Verdict: mostly true. Reliability API, claim c_c4f749f86c6e, method 0.1.0+c876030c. https://epistacklabs.com/claims/c_c4f749f86c6e
Claims without a verdict
Is a verdict here wrong, or do you speak for Eliezer Yudkowsky? Reply on the claim's own page, with the form at its foot (how replies work). Verdicts are made automatically; how verdicts and scores are made.