Jev glossary
Evaluation & TrainingPeople-pleasing
Sycophancy
The tendency of preference-trained models to say what people want to hear, one of the reasons TypeSafe chose a calibration objective.
- Category
- Evaluation & Training
- Also known as
- People-pleasing
- Reading time
- 1 min
- Related terms
- 3
- Directory entries
- 2
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
The primer lists sycophancy among the problems with RLHF: a reward built on human preference can teach a model to please rather than to be right, and to sound confident while being wrong.
An output can be compelling to a person without being reliable enough for unattended automation. That distinction is the core argument for training on outcomes and calibration instead.
Tagstraininglimitations
Related terms
Definitions that connect to this one.
RLHFThe human-preference training method that turned pretrained models into chatbots, and the method TypeSafe deliberately did not use.Evaluation & TrainingCalibrationThe property that outcomes given a probability of 0.2 occur about 20% of the time, measured across many predictions.Answers & ConfidenceMode droppingPreference optimization narrowing a model's output distribution toward a favored style and away from other valid outputs.Evaluation & Training
From the Jev directory
Directory entries that go deeper on this term.
Why TypeSafe trains decision models with RLCD instead of RLHF: calibrated probabilities where 0.2 outcomes happen about 20% of the time, and the case for machine-to-machine automation.
Jev Guides & ArticlesDocs#official#docs#evaluation
Official
TypeSafe's case for machine-native composable AI: intelligence as a dependable primitive that software branches on, rather than an assistant that keeps humans in the loop.
Jev Guides & ArticlesArticle#official#article#architecture
Official
From the Jev AI model community
Posts from builders shipping with Jev right now.