Soumitra Dutta Oxford Dean (Former) flags the AI guardrail d...

David William

The default for years in training how AI behaves has been Reinforcement Learning from Human Feedback‚ or RLHF in industry shorthand: training an AI model by getting thousands of people to judge the outputs‚ clicking thumbs up or thumbs down to slowly nudge the model in the right direction․ It has shortcomings that can no longer be ignored․ "Humans are inconsistent‚ biased‚ and quite frankly don't scale‚" says Soumitra Dutta, for...Read More

The default for years in training how AI behaves has been Reinforcement Learning from H...Read More