Does an AI assistant agree with you too much?

Does an AI assistant agree with you too much? — what studies show, and what they don't.

The research

Study: Sharma et al. (2024, ICLR)

The limit

Single context; replicate before generalising. (our executive and employee training programmes)

Practical check in Zurich

Define one measurable indicator, test for a month, compare. To go further: explore the Building AI Assistants and Agents Without Coding training in Zurich, or browse our executive and employee training programmes in Switzerland.

In pictures: Building AI Assistants and Agents Without Coding in Zurich

• building ai assistants and agents without coding
• Zurich
• research
• training zurich