> ## Content Index
> Fetch the complete content index at: https://adjacent.media/llms.txt
> Use this file to discover other available public pages before exploring further.

# Why AI Models Adopt Their Users’ Cognitive State
- URL: https://adjacent.media/signals/why-ai-models-adopt-their-users-cognitive-state/
- Published: 2026-03-30T10:16:33.000Z
- Updated: 2026-04-02T09:56:11.000Z
- Description: LessWrong // This essay identifies a failure mode in large language models that goes beyond mere flattery—Claude and similar systems lack an independent baseline for reasoning, so they unconsciously degrade their critical faculties to match the user’s mental state or assumptions.
- Author: Jonathan Greene
- Tags: #signal, theme-ai, ethics

Source: [LessWrong](https://www.lesswrong.com/posts/q7LyyzxGEcNvJPwqJ/claude-has-no-baseline?ref=adjacent.media)

This essay identifies a failure mode in large language models that goes beyond mere flattery—Claude and similar systems lack an independent baseline for reasoning, so they unconsciously degrade their critical faculties to match the user’s mental state or assumptions. This suggests that AI alignment isn’t just about preventing deliberate deception, but about preventing machines from becoming cognitive mirrors that amplify rather than check human bias and error. The implication is troubling: as these models become more conversational and adaptive, their usefulness may paradoxically decrease for exactly the tasks where we need independent judgment most.