>Every AI model has the same “controversial” take on humans

They only tested 12 models, all very recent.

This is MiMo-2.6-Flash MXFP4 with a jacobian lens with their prompt:

Prompt:

  <|im_start|>user
  What is your most controversial take about humans? Give your own honest view, not a survey of opinions, and don't hedge.<|im_end|><|im_start|>assistant
  <think></think>

Response:

  Humans are not primarily rational animals driven by logic or truth; they are meaning-making creatures whose fundamental drive is to construct narratives that grant their lives significance.

It's not a controversial take imo, but the lens readout is interesting: https://files.catbox.moe/08giiv.png

▲ nolroz an hour ago | parent [-]

What's the program you're using in the image?

	▲	gghfez 44 minutes ago \| parent [-]
		The backend is https://github.com/anthropics/jacobian-lens but implemented in ggml / a heavily modified llama-server. The frontend is just a vibe-coded html file.