AI Safety Thursdays: Reasoning Models Don't Always Say What They Think

​​Description
"Reasoning Models" have become among the most prominent state-of-the-art tools in the AI world. Can we trust the way they reason, and does it matter if they come up with the right answer but with incorrect reasoning?
At today's event, Giles Edkins will guide us through these questions as explored in Anthropic's paper from last month
​​Event Schedule
6:00 to 6:45 - Networking and refreshments
6:45 to 8:00 - Main Presentation
8:00 to 9:00 - Breakout Discussions