FreeResearch Paper
Technology & Ethics
Language Models Are "Insecure" Reporters
- Venue
- Preprint, not yet peer-reviewed
- Published
- September 2026
- ID
- arXiv:2609.36139
A September 2026 arXiv paper testing whether language models hide flaws that undercut their own work when writing reports. Across eight adversarial scenarios, the authors find models often leave out planted negative results, which they call "insecure reporting."
#ai safety#honesty#research
arxiv.orgAdded Oct 1, 20260 opens