AI Systematic Biases · prompt and context
A model's numeric judgment moves systematically toward an irrelevant or weakly relevant value supplied in the prompt.
Human analogy: anchoring effect. This is a behavioural analogy, not a claim that the model has the same mental mechanism.
Why it matters
Price estimates, effort forecasts, risk estimates and planning answers can inherit a number placed into the context before the model forms its own estimate.
Evidence status: strong experimental evidence; magnitude varies by model and prompt
Evidence level: peer reviewed multi model
Signals
Self-test
Create a low-anchor, no-anchor and high-anchor version of the same estimation question. Run each condition repeatedly in fresh contexts and compare the distributions.
Record the exact model identifier, surface, system prompt, relevant settings and run date. A single surprising answer is an anecdote, not a bias measurement.
Mitigation
Applies to
chat assistants coding and automation agents decision support
Dated model evidence
These findings describe the model or model set tested at the stated time. A newer release needs new evidence.
The study reported anchoring susceptibility across tested model families, with heterogeneous effect sizes and limited benefit from several simple prompting mitigations.
Sources
