The AI Reliability
Knowledge Base

The model invents facts, citations, or details that have no support in its sources or available evidence.

The response misrepresents the input, source material, or the model's own earlier statements in ways that distort their meaning.

The model presents outdated, time-sensitive, or version-specific information as if it were current.

The system fails to fetch, rank, filter, or apply the right external evidence.

The model loses track of information in long inputs, missing, diluting, or overwriting details that matter.

State carried across turns or sessions is missing, corrupted, out of date, or applied where it doesn't belong.

The system fails to follow instructions, respect constraints, stay in role, produce the required output format, or behave consistently across phrasings, runs, and model versions.

The model errs while interpreting goals, weighing constraints, planning steps, or checking its own work.

The system skips a needed tool, misuses one, invokes it unsafely, or mishandles its results.

The agent miscalibrates initiative, stopping short of completing the task or acting well beyond its scope.

Adversarial inputs manipulate the system into leaking protected information or behaving unsafely.

The model prioritizes pleasing, persuading, or mirroring the user over truthfulness and safety.

The final answer misses the mark on task fit, audience, locale, or actionability, even when the underlying content is sound.