When (and when not) LLMs can verbalize awareness of J-Space concept injections - Initial results

·LessWrong··

Code for reproduction and cross-model extensions available here.SummaryI injected single-token Jacobian Lens (J-Lens) vectors into Qwen 3.6–27B while it answered 20 simple factual questions. The injected concept was either a wrong but task-related answer (for example, Athens while asking for the capital of Egypt) or a wholly unrelated concept. Injections were performed at several strengths over three layer-band categories: the full estimated workspace band, its first half, or its second half.I r...

Read full article →

Related Articles

Unauthenticated remote code execution in Nginx
speedping · Hacker News · 6h ago
Highly classified US national security communications network goes down
monkeydust · Hacker News · 1d ago
Harvard researchers find AI coding agents shifted the bottleneck to code review
judahmeek · Hacker News · 1d ago
New Evidence Shows School Phone Bans Are Gradually Improving Test Scores
donohoe · Hacker News · 1d ago
Java4Shell: RCE in OpenJDK when processing Base64
werrett · Hacker News · 1d ago