The story’s score and claims

Comments on No. 95 of 106 · SingularityHub · edition of Thursday 12 November 2026

AI Models Can Tell When Researchers Plant Concepts in Their Neural Networks

Summary

Researchers at NYU and the University of Texas, building on Anthropic's 2025 work, found that large open models such as Qwen3-235B and Llama 3.1 405B can flag when activity patterns for concepts have been artificially injected into their networks, detecting injections up to 53.9 percent of the time without false…

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules