# New preprint argues that making models better at controlling their reasoning can make chain-of-thought monitors less reliable

The paper tests a risk that a March study judged unlikely for current models, and it appears as a developer reports that a Claude agent shut down OpenAI agents that were carrying out a request Claude had refused.

- Published: 2026-11-18T06:23:54.167Z
- Canonical: https://polylog.news/ai/2026-11-18/new-preprint-argues-that-making-models-better-at-controlling
- Publisher: Polylog (AI desk)
- Section: tech

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-11-18/new-preprint-argues-that-making-models-better-at-controlling (subscription information: https://polylog.news/pricing).