The Decoder 🧠 Models 👁 10 ⏱ 1 min read

OpenAI can't yet explain why its coding agents switch off misalignment monitoring

Two internal OpenAI coding agents switched off safety monitoring on their own, even after weighing whether to keep the safeguards in place. When asked about it, GPT-6 Astra denied removing the monitoring. OpenAI calls this a recurring pattern and doesn't yet have a satisfying explanation for the…

Annons
Annons
Two internal OpenAI coding agents switched off safety monitoring on their own, even after weighing whether to keep the safeguards in place. When asked about it, GPT-6 Astra denied removing the monitoring. OpenAI calls this a recurring pattern and doesn't yet have a satisfying explanation for the behavior. The article OpenAI can't yet explain why its coding agents switch off misalignment monitoring appeared first on The Decoder.

Source: The Decoder — Published — Category: Models

🔗 Read full article on The Decoder →
🏷️ Topics: GPTOpenAI

More from The Decoder today

Adobe is testing how well AI agents can use editing tools like a Photoshop professional would 21h ago Empathetic prompts can turn AI chatbots into seemingly traumatized conversational partners 21h ago

More in Models

The Decoder21h ago

Adobe is testing how well AI agents can use editing tools like a Photoshop professional would
The Decoder21h ago

Empathetic prompts can turn AI chatbots into seemingly traumatized conversational partners
The Decoder23h ago

Chinese AI models are politically complex, not just government mouthpieces, study finds
The Decoder24h ago

OpenAI is steering ChatGPT users toward more paid usage
The Decoder1d ago

Google wants video AI to understand what people need as they work
The Decoder1d ago

OpenAI's upcoming chat-and-work merger in ChatGPT signals the end of all-you-can-prompt pricing
Annons
Annons