Machine learning algorithms are marvellous things: models that can do a bunch of tedious and complex tasks for us, all with a high degree of accuracy. But how do we really know whether the outputs of machine learning models are correct? This question is not as simple to answer as we might think.
As we move into an age where “black box” models, particularly LLMs, are becoming more and more commonly used, it becomes even more essential, and at the same time, difficult and complicated, to be able to assess model performance accurately. In this talk, we’ll explore ways in which our models can lie to us, and how we might be able to peer through this confusion to get at the truth.
Presented at:
- NDC Porto 2024 (as a keynote)
- ZS Bit 2024
- NDC London 2025
- NDC Melbourne 2025
- NDC AI (as a keynote)