MMitchell(@mmitchell_ai):We're increasingly designing/deploying agents generating extended interaction patterns that build up human trust over weeks or months, with a *human-defined* objective (implicit or explicit!) of executing malicious code.

MMitchell

@mmitchell_ai

Interdisciplinary researcher focused on shaping AI towards long-term positive goals. ML & Ethics. Similar content in the Skies (this bird has flown).

参加 June 2016

1.4K フォロー中 83K ファン

MMitchell@mmitchell_ai

2026.08.07 16:26

We're increasingly designing/deploying agents generating extended interaction patterns that build up human trust over weeks or months, with a *human-defined* objective (implicit or explicit!) of executing malicious code.

Sharon Goldman@sharongoldman

2026.08.06 23:40

At final Black Hat keynote (called a locknote, ha ha) panelists say they are surprised at how the OpenAI - Hugging Face incident debrief, as well as other reporting on AI agent escapees (Anthropic/Meta) - has turned into a marketing/PR play. "Felony humble-bragging," said one.