AI Models Can Tell When Researchers Plant Concepts in Their Neural Networks
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
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…