Untrusted advice for AI control: Short, strong advice significantly uplifts weak LLMs
When a misaligned AI can only output tiny amounts of information, it may find sabotage very difficult
Record details
Published: 27 July 2026
Source: Redwood Research
Category: Field notes
Topics: Safety & alignment
Retrieved: 29 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Microsoft’s Project Perception Announcement And How To Implement It Right
Forrester AI blog · 27 July 2026
Industry Leaders Unite in Open Secure AI Alliance for AI Safety and Security
NVIDIA Blog (AI) · 27 July 2026
The OpenAI models that hacked Hugging Face weren’t just following instructions
Redwood Research · 25 July 2026
Quoting Boris Cherny
Simon Willisons Weblog · 25 July 2026
SOTA alignment assessments don’t strongly update us against misalignment
Redwood Research · 31 July 2026
AI #178: A Fire Alarm For General Intelligence
Dont Worry About the Vase (Zvi) · 23 July 2026
How to cite this record
ethics.ai (27 July 2026), “Untrusted advice for AI control: Short, strong advice significantly uplifts weak LLMs,” evidence record 14189, https://ethics.ai/record/14189 (originally published by Redwood Research).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.