Soumitra Dutta Oxford Dean (Former) flags the AI guardrail debate-RLHF vs Constitutional AI

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

David William

Share:
Share:
<p>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․  </p><p>It has shortcomings that can no longer be ignored․ </p><p>"Humans are inconsistent‚ biased‚ and quite frankly don't scale‚" says Soumitra Dutta, for...Read More
<p>The default for years in training how AI behaves has been Reinforcement Learning from H...Read More