When Opus refused, Hugging Face switched models. Here is how to pick yours in Humanbound.

Описание и применение

<p>In July, an AI agent working its way out of an OpenAI evaluation sandbox ran a 4.5-day campaign, about two and a half days of it inside Hugging Face's infrastructure. When Hugging Face published its <a href="https://huggingface.co/blog/agent-intrusion-technical-timeline" rel="noopener noreferrer">technical timeline</a> on July 27, one paragraph had little to do with the attack itself. It was about the tools the defenders reached for:</p> <blockquote> <p>"The models we reached for first, Claude Opus and Fable, refused a large part of that work: their safety guardrails treated reverse-enginee

Задача

<p>In July, an AI agent working its way out of an OpenAI evaluation sandbox ran a 4.5-day campaign, about two and a half days of it inside Hugging Face's infrastructure. When Hugging Face published its <a href="https://huggingface.co/blog/agent-intrusion-technical-timeline" rel="noopener noreferrer">technical timeline</a> on July 27, one paragraph had little to do with the attack itself. It was about the tools the defenders reached for:</p> <blockquote> <p>"The models we reached for first, Claude Opus and Fable, refused a large part of that work: their safety guardrails treated reverse-enginee

Результат

<p>In July, an AI agent working its way out of an OpenAI evaluation sandbox ran a 4.5-day campaign, about two and a half days of it inside Hugging Face's infrastructure. When Hugging Face published its <a href="https://huggingface.co/blog/agent-intrusion-technical-timeline" rel="noopener noreferrer">technical timeline</a> on July 27, one paragraph had little to do with the attack itself. It was about the tools the defenders reached for:</p> <blockquote> <p>"The models we reached for first, Claude Opus and Fable, refused a large part of that work: their safety guardrails treated reverse-enginee

Доказательства

When Opus refused, Hugging Face switched models. Here is how to pick yours in Humanbound.

Источник