Anthropic develops a Jacobian lens to probe inside Claude and reveals what large language models do when answering questions and performing tasks
Read the original at www.technologyreview.com→The AI firm Anthropic has developed a technique that has given it the clearest glimpse yet at what’s really going on inside large language models as they answer questions or carry out tasks. What they found ranges...
Original headline: "Anthropic found a hidden space where Claude puzzles over concepts"