MIT Team Teaches AI Models What They Didn’t Know
The use of artificial intelligence (AI) is growing rapidly and becoming increasingly intertwined with our daily lives and high-stakes industries such as healthcare, telecommunications, and energy. But with great power comes great responsibility: AI systems sometimes make mistakes or provide uncertain answers that can have significant consequences.
Why is this so important?
Many AI models, including advanced ones, can sometimes produce so-called ‘hallucinations’—they provide incorrect or unfounded answers. In sectors where decisions carry serious consequences, such as medical diagnosis or autonomous driving, this can have disastrous effects. Themis AI developed Capsa, a platform that applies uncertainty quantification: it measures and quantifies the uncertainty of AI outputs in a detailed and reliable manner.
How does it work?
By making models uncertainty-aware, they can attach a risk or confidence label to their outputs. For example, a self-driving car can indicate that it is uncertain about a situation and therefore activate human intervention. This not only improves safety but also increases users’ trust in AI systems.
- When integrating with PyTorch, the model is wrapped using
capsa_torch.wrapper()where the output consists of both the prediction and the risk:
For NetCare and its clients, this technology represents a huge step forward. We can deliver AI applications that are not only intelligent, but also safer and more predictable, with a lower risk of hallucinations. It helps organizations make better-informed decisions and reduce risks when implementing AI in business-critical applications.
Conclusion
The MIT team shows that the future of AI is not only about becoming smarter, but above all about operating more safely and fairly. At NetCare, we believe that AI only becomes truly valuable when it is transparent about its own limitations. With advanced uncertainty quantification tools such as Capsa, you can put this vision into practice.
