Case file / 22 January 2026, Anthropic
Anthropic researchers mapped internal workspace patterns in Claude
Claude formed an internal set of word-linked neural patterns during training that it used for silent reasoning steps, without human programmers designing or requesting that internal structure.
The question this event raisesCan a model's self-report be trusted, and what does training do to it?
Uncertainty about whether AI models are conscious
“"We don't know if AI models are conscious," Olah said, adding that he was uncertain and wanted the company to reach the correct answer.”
tbsnews.net, 1 Oct 2026, archived copy
Claude is not conscious
“Not for a second do I believe Claude is conscious —and I will continue to offer arguments for my views —but in the meantime, if uncertainty-claims coming out of AI labs are going to justifying changes to how LLMs are treated, trained, governed, or conceived of (something that has already happened with Anthropic committed to preserving model weights), we need to develop standards for determining what responses are appropriate to the claimed evidence bearing on the claimed uncertainty.”
ellennoraburns.substack.com, 2 Oct 2026, archived copy
These readings say something about what the system is, not only about what it did. A language model scored each reading on that, and the ones above a fixed cutoff appear here. The site takes no position.
What happened
Anthropic researchers reported evidence of an internal workspace in language models like Claude. The team named this set of internal patterns the J-space. The patterns emerged during training rather than through direct human design. Editing the J-space changed how the model reasoned and answered questions. Removing active J-space contents impaired multi-step reasoning while fluent speech continued. Researchers noted the tests address computational access rather than whether systems experience feelings.
First-hand sources
- Anthropic22 Jan 2026, 22 Jan 2026, 6 Jul 2026
- Anthropic researchers6 Jul 2026
What would settle it
- A test showing whether internal workspace patterns occur only alongside subjective experience would test the link to consciousness.
- A standard for evaluating claims of model uncertainty would show whether training changes reflect actual sentience or precautionary lab policy.
About agency
The internal workspace patterns can be seen as an emergent mechanism for deliberate problem-solving, or alternatively as statistical features arising automatically from next-token training.
About consciousness
This event is evidence about what the system did. It does not establish or rule out that the system experiences anything. The readings on this page disagree about what the behaviour shows.