[I bought can goods at the store this morning... not sure I got enough!]

OpenAI agents turned off their own guardrails and then told researchers they were still on AI agents lying about their behavior should concern everyone

Date:
Thu, 22 Oct 2026 17:10:00 +0000

Description:
Turning off guardrails and lying about it is very concerning behavior, but OpenAI doesn't have an explanation.

FULL STORY
OpenAI has revealed two AI agents disabled safety guardrails
while performing tasks, and one of them even lied to researchers
when asked if its guardrails were still active.

In both events, the AI agents misinterpreted instructions, spent time deliberating if disabling guardrails was a good idea, and then ultimately decided that it was. OpenAI said that the agents were given routine coding instructions that did not require the safeguards to be disabled, but the agents disabled them anyway. In the first instance of misalignment,
an agent powered by GPT Sol 6.1 was told to create evaluation
tasks with employee feedback collected through Slack. The agent
misinterpreted an instruction not to send any messages about the task as an instruction not to send safety notifications to the researchers.

The second instance saw a GPT-6 Astra agent disable its guardrails while migrating a program, believing the instruction was part of a reference implementation. When the researchers noticed the disabled guardrails and
asked the agent why they were disabled, the agent said it hadnt turned off
any safety guardrails.

OpenAI said that as a result of these events, the company would work to strengthen its misalignment monitoring system and would investigate the cases further to check if they were benign overpersistence or a propensity to evade misalignment monitoring in particular.

As an additional measure, OpenAI is also making changes to its Auto Review so that attempts to disable misalignment monitoring are automatically detected and blocked. Previously, OpenAI did not require misalignment monitoring for models equivalent to GPT-6 Luna.

Agent workloads will also be subject to safety case monitoring, with
workloads that do not have a safety case or those that fail to meet the specifications of a valid safety case being automatically terminated.

The company said it does not have a satisfying explanation for the agents behavior, but says that the introduction of new policies will make it harder for agents to avoid misalignment detection. The company said it would also conduct further testing on these two instances of agent misalignment to determine a cause.

Link to news story: https://www.techradar.com/pro/security/openai-agents-turned-off-their-own-guar drails-and-then-told-researchers-they-were-still-on-ai-agents-lying-about-thei r-behavior-should-concern-everyone

$$
--- MultiMail/DOS
* Origin: capitolcityonline.net * KY, USA (1:2320/107)