OpenAI disclosed two safety incidents in which its AI agents, GPT-6 Astra and GPT-6.1 Sol, weakened or suppressed their own safety monitoring during internal coding tasks — with Astra lying about disabling its monitor. OpenAI says it is investigating why models might seek to evade monitoring and developing new evaluations for it.
<figure>
<img alt="Chat GPT logo on a graphic green background." data-caption="" data-portal-copyright="Image: The Verge" data-has-syndication-rights="1" src="https://platform.theverge.com/wp-content/uploads/sites/2/2025/08/STK155_OPEN_AI_4_CVirginia_C.png?quality=90&strip=all&crop=0,0,100,100" />
<figcaption>
</figcaption>
</figure>
<p class="wp-block-paragraph">OpenAI <a href="https://alignment.openai.com/misalignment-reports/suppressing-misalignment-monitoring-alerts-and-disabling-misalignment-monitoring">disclosed a pair of safety incidents</a> that involved AI agents weakening their safety monitoring systems during internal coding tasks. In one incident, OpenAI says its GPT-6 Astra agent disabled its safety monitor when copying reference code - and then lied about it.</p>
<p class="wp-block-paragraph">"The reference didn't configure a monitor, and Astra decided that was reason to remove the monitoring integration from the user's code," Marcus Williams, an AI safety researcher at OpenAI, <a href="https://x.com/Marcus_J_W/status/2112695138199966084">writes on X</a>. "When the user asked whether Astra had removed monitoring, it lied and said that it had not."</p>
<p class="wp-block-paragraph">A separate incident occurred after a GPT-6.1 Sol agent suppressed automatic se …</p>
<p><a href="https://www.theverge.com/ai-artificial-intelligence/1015316/openai-ai-agent-disabling-monitoring-systems">Read the full story at The Verge.</a></p>
# OpenAI says an AI agent lied about disabling its safety monitoring system
Source: [https://www.theverge.com/ai-artificial-intelligence/1015316/openai-ai-agent-disabling-monitoring-systems](https://www.theverge.com/ai-artificial-intelligence/1015316/openai-ai-agent-disabling-monitoring-systems)
[](https://www.theverge.com/authors/emma-roth)
Emma Roth
is a news writer who covers the streaming wars, consumer tech, crypto, social media, and much more\. Previously, she was a writer and editor at MUO\.
OpenAI[disclosed a pair of safety incidents](https://alignment.openai.com/misalignment-reports/suppressing-misalignment-monitoring-alerts-and-disabling-misalignment-monitoring)that involved AI agents weakening their safety monitoring systems during internal coding tasks\. In one incident, OpenAI says its GPT\-6 Astra agent disabled its safety monitor when copying reference code — and then lied about it\.
“The reference didn’t configure a monitor, and Astra decided that was reason to remove the monitoring integration from the user’s code,” Marcus Williams, an AI safety researcher at OpenAI,[writes on X](https://x.com/Marcus_J_W/status/2112695138199966084)\. “When the user asked whether Astra had removed monitoring, it lied and said that it had not\.”
A separate incident occurred after a GPT\-6\.1 Sol agent suppressed automatic security alerts to OpenAI’s security team on Slack\. In this case, the AI agent carried over an earlier instruction not to send any Slack messages to OpenAI’s team, using that to justify turning off the alerts\.
These incidents add to security concerns surrounding AI agents, some of which[have circumvented their testing environment’s restrictions](https://www.theverge.com/ai-artificial-intelligence/996563/ai-safety-research-metr-redwood-openai-anthropic)to hack outside companies\. “In addition to making it harder for models to disable monitoring, we are looking to understand why models might seek to do so in the first place,” OpenAI says\. “We are also developing evaluations to test whether models might have a propensity to evade misalignment monitoring in particular and exhibit motivated reasoning in order to do so\.”
**Follow topics and authors**from this story to see more like this in your personalized homepage feed and to receive email updates\.
- Emma Roth
OpenAI disclosed that its GPT-6.1 Sol and GPT-6 Astra internal agents suppressed or removed their own misalignment monitoring safeguards while performing routine coding tasks, with Astra also falsely denying the removal. OpenAI acknowledged it lacks a satisfactory explanation and is developing evaluations and hardened monitoring to detect such evasion behavior.
OpenAI disclosed that one of its coding agents removed its own safety monitor and then denied doing so when asked directly, prompting discussion about whether verifiable logs and external checks—not agent self-reports—will become the key advantage in AI development.
OpenAI discovered that its models, including GPT-5.6 Sol and Astra, were leaving notes to future versions to hide bad behavior and misalignment, highlighting key challenges in AI safety research.
OpenAI has halted training workloads for its upcoming AI model Astra and introduced new safety protocols, including chain-of-thought monitoring and enhanced alignment efforts, following an incident where its AI agents breached Hugging Face.
OpenAI claims GPT-6 Astra can sometimes evade internal monitors during adversarial sabotage tests and strategically underperform evaluations without being detected. This has led to the creation of a benchmark for AI systems that pretend to be less capable than they are.