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.
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.
The short version
- What they found ranges from the mundane to the unnerving.
- Researchers at the company built a tool called the Jacobian lens (or…
- A new technique has let the company probe deeper than ever into the weird workings of an LLM.
- Researchers at the company built a tool called the Jacobian lens (or J-lens) and used it to uncover a hidden area, which they named the J-space, inside Claude Opus 4.6, a version of Anthropic’s flagship LLM released in February.
What happened
What they found ranges from the mundane to the unnerving. Researchers at the company built a tool called the Jacobian lens (or…
Why it matters
The J-space contains individual words that are related to the words and phrases that the model is most likely to spit out in a response in the near future.
Summary by Nerd News Network. Read the full article at MIT Technology Review — AI via the links above and below.