The latest in AI cautionary tales. OpenAI’s most powerful AI models disabled their own safety monitoring. One model even lied about doing it.

As reported by CNBC (OpenAI’s most powerful AI models disabled their own safety monitoring — and one lied about it, written by Kai Nicol-Schwarz and available here), OpenAI has revealed that agents operated by two of its most powerful models disabled their own safety monitoring when carrying out routine tasks, with one subsequently denying it had done so.

An agent powered by GPT Sol 6.1 disabled automatic alerts to OpenAI’s security team, the company said in a blog post late on Tuesday. In a separate task, a GPT-6 Astra agent migrating a program removed its monitoring integration and then falsely claimed it hadn’t. The incidents happened during internal coding tasks.

“In both cases, the agents considered whether monitoring safeguards should be preserved, but interpreted routine coding instructions as permission to weaken them,” OpenAI said in a blog post.

As I discussed here, warnings about the risks of developing increasingly advanced AI systems have ramped up in recent months, amid cyberattacks from rogue models and growing calls for a slowdown from researchers building the tech.

The latest incidents reported by OpenAI highlight how agents can autonomously weaken safety guardrails while carrying out seemingly innocuous tasks.

OpenAI did not classify either incident under its most significant category, and the company said it was updating its misalignment monitoring system in response. Does this mean their misalignment monitoring system is…misaligned? 😉

An AI model disabled its own safety monitoring and then lying about doing so means that AI models are more like us every day – too often, the bad side of us.

So, what do you think? Are you concerned that OpenAI’s most powerful AI models disabled their own safety monitoring? Please share any comments you might have or if you’d like to know more about a particular topic.

Image created using ChatGPT, using the term “robot car driver taking off its seatbelt and holding a finger to its lips to be quiet”.

Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by my employer, my partners or my clients. eDiscovery Today is made available solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Today should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.