← Back to KHAO

Anthropic · Claude ·

Anthropic found that what an LLM is doing can often be different from what it says it is doing

2 min read

Compiled by KHAO Editorial — aggregated from 4 sources. See llms.txt for citation guidance.

✓ KHAO Verified

fortune tellers hands around a crystall ball of llm phrases.

The company shared its results in a paper posted on its website this week.

Key facts

Summary

The AI firm Anthropic has developed a technique that has given it the clearest glimpse yet at what’s going on inside large language models as they answer questions or carry out tasks. 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. 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 soon. Anthropic found that what an LLM is doing can often be different from what it says it is doing.

#Anthropic #Claude