AI hallucination
Concept
An AI hallucination is a confident response by an AI model, such as a large language model, that is not justified by its training data or sources, for example invented or incorrect facts.
| Type | Concept |
|---|---|
| Wikipedia | en.wikipedia.org/wiki/Hallucination_(artificial_intelligence) |
Articles about AI hallucination (2)
- Можно ли использовать ИИ для написания тест-кейсов по пользовательским историям? На что смотреть в первую очередь
· Mirko Peters
Можно ли генерировать тест-кейсы по пользовательским историям с помощью ИИ? Исследования показывают быстрые черновики с пробелами. Что проверить в первую очередь: покрытие, неодноз - Can AI write test cases from user stories? What to check first
· Mirko Peters
Can AI generate test cases from user stories? Studies show fast drafts with gaps. See what to check first: coverage, ambiguity, edge cases and invented tests.
Community wiki
Short info above, community knowledge below: add practical tips, examples or corrections. New contributions are reviewed first; trusted members publish directly.
Experts and companies for this topic
- Mirko Peters · Microsoft MVP
Sources
- Wikipedia: en.wikipedia.org/wiki/Hallucination_(artificial_intelligence)
- Feed for this topic (RSS): entity/ai-hallucination/feed.xml
- Articles on this topic: 2
Maintained by Mirko Peters (Microsoft MVP) · Last updated: