A new training method improves the reliability of AI confidence estimates without sacrificing performance, addressing a root cause of hallucination in reasoning models. Read More
Teaching AI models to say “I’m not sure”
A new training method improves the reliability of AI confidence estimates without sacrificing performance, addressing a root cause of hallucination in reasoning models.
Related Posts
In our latest podcast, hear how the “Smokejumpers” team brings Gemini to billions of people.
The latest episode of the Google AI: Release Notes podcast focuses on how the Gemini…
Gemini 3.1 Flash Live: Making audio AI more natural and reliable
Gemini 3.1 Flash Live is now available across Google products.
ACM Human-Computer Interaction Conference (CHI) 2026
Read More