Why you shouldn't leave model selection on default in Copilot, Gemini and other AI tools
When analyzing data, Microsoft Copilot invents country differences where none exist. Mathematician Adam Kucharski fed the tool identical datasets with different country labels, and Copilot delivered detailed stereotypes instead of accurate results. Thinking models catch the trick, but only if users know when to reach for them.
Article intelligence
Key points
- Microsoft Copilot invented stereotypes when given identical datasets with different country labels.
- Thinking models can catch the trick but require user awareness.
- Default model selection in AI tools can lead to inaccurate results.
Why it matters
This matters because microsoft Copilot invented stereotypes when given identical datasets with different country labels.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
When analyzing data, Microsoft Copilot invents country differences where none exist. Mathematician Adam Kucharski fed the tool identical datasets with different country labels, and Copilot delivered detailed stereotypes instead of accurate results. Thinking models catch the trick, but only if users know when to reach for them.
The article Why you shouldn't leave model selection on default in Copilot, Gemini and other AI tools appeared first on The Decoder.