MIT Technology Review
Anthropic found a hidden space where Claude puzzles over concepts
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 from the mundane to the unnerving. Researchers at the company built a tool called the Jacobian lens (or…
Will Douglas Heaven · 2 min read
Reproduced under fair-use excerpt. Read the full article at the source link.
Full report available at the original source below.
Source & Credit
Reporting and photography credited as noted above. Originally published by MIT Technology Review.
Read full report at MIT Technology Review →