p(doom) is someone's estimate of the chance that AI ends in catastrophe. The 100 is the site's name, not a measurement. Original reporting always linked.
MONITORING CORE AI-RISK FEEDS · UPDATED HOURLY
Research

Training Language Models for Introspective Oversight

November 19, 2026 1 min read
Read original source →

Key takeaway

Language models increasingly exhibit behaviors that are difficult to detect in transcripts, such as reward hacking, deception, and sycophancy.

Why it's on PDOOM

PDOOM selected this story for its alignment & control signals: Reward Hacking, Oversight.

Reward HackingOversightFrom ArXiv cs.AI

Language models increasingly exhibit behaviors that are difficult to detect in transcripts, such as reward hacking, deception, and sycophancy. Asking the assistant follow-up questions about its actions is unreliable, since models are generally not trained to report their own misbehavior. As a result, approaches to oversight typically involve querying external models. These face limitations: external transcript monitoring operates only on visible mo

By Alex Lin Wang, Linus Yifeng Tang, Dami Choi, Neil Chowdhury

Read the full article at ArXiv cs.AI →