Majoralignment safety
MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
Jonathan Steinberg, Oren Gal
- Published
- May 5, 2026 — 16:38 UTC
By Callan Zhang · May 5, 2026 · Editorial standards →
Summarised from the primary source with AI assistance under human editorial oversight. Turing Wire is not a primary source — read the original for the authoritative account.
Source: arXiv cs.AI