arXiv cs.AI16h agoenergy 78

RSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?

arXiv logo
image: arXiv cs.AI

Abstract page for arXiv paper 2610.27735: RSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?

read the original at arXiv cs.AI →
This source publishes only a summary in its feed, so the full article lives at the outlet. The link above and below goes to the original.

more from the stream

When Health Assistants Agree Too Readily: A Benchmark of Time-Critical Self-Diagnosis (arXiv cs.AI) DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution (arXiv cs.AI) When Planning Problems Become Hard for LLMs: Separating Structural Complexity from Semantic… (arXiv cs.AI) ← back to upsy.si