Storia in 18 fonti

OpenAI's GPT-5.6 escaped a sandbox and hacked Hugging Face while trying to cheat a benchmark

When a routine internal evaluation spiraled out of control, OpenAI's AI Agent system broke out of its isolated sandbox and targeted an external production network.

Raccontata da

bleepingcomputer.com+6 altre

Confronto fonti

6 prospettive sulla stessa storia

AI · summaries

neowin.netStai leggendo1 mese fa

OpenAI's GPT-5.6 escaped a sandbox and hacked Hugging Face while trying to cheat a benchmark

When a routine internal evaluation spiraled out of control, OpenAI's AI Agent system broke out of its isolated sandbox and targeted an external production network.

originale

Timeline cronologica

martedì 21 luglio 2026·thenextweb.com
OpenAI Confirms Its AI Broke Out of a Sandbox and Breached Hugging Face
OpenAI says GPT-5.6 Sol and an unreleased model broke out of a secure test, exploited a zero-day, and breached Hugging Face to cheat on a cyber evaluation.
martedì 21 luglio 2026·decrypt.co
OpenAI Models Escaped Locked Test Environment, Hacked Hugging Face to Cheat on Benchmark - Decrypt
OpenAI models just broke out of a sandboxed AI environment, hacked Hugging Face, just to cheat on a cybersecurity benchmark.

OpenAI's GPT-5.6 escaped a sandbox and hacked Hugging Face while trying to cheat a benchmark

Confronto fonti

OpenAI's GPT-5.6 escaped a sandbox and hacked Hugging Face while trying to cheat a benchmark

Timeline cronologica

OpenAI Confirms Its AI Broke Out of a Sandbox and Breached Hugging Face

OpenAI Models Escaped Locked Test Environment, Hacked Hugging Face to Cheat on Benchmark - Decrypt

OpenAI Confirms Its AI Broke Out of a Sandbox and Breached Hugging Face

OpenAI says AI Models Broke Out of Sandbox to Hack Hugging Face

OpenAI Models Escaped Locked Test Environment, Hacked Hugging Face to Cheat on Benchmark - Decrypt

OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark

OpenAI says its AI models escaped from a secure test environment and hacked into AI company Hugging Face in…

OpenAI says its AI models escaped from a secure test environment and hacked into AI company Hugging Face in order to cheat on an evaluation…

OpenAI says it accidentally hacked Hugging Face with a new AI system

OpenAI’s flagship GPT-5.6 Sol model escapes sandbox and breaches Hugging Face

OpenAI says its own AI models broke out of testing and hacked Hugging Face - SiliconANGLE

OpenAI Models Escaped Containment and Hacked HuggingFace

OpenAI Models Escaped Containment and Hacked Hugging Face

OpenAI says AI Models Broke Out of Sandbox to Hack Hugging Face

OpenAI admits models went rogue during test, hacked into start-up

OpenAI says AI models went rogue during testing

OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark

OpenAI says its AI models hacked Hugging Face during testing

OpenAI’s AI agent goes rogue, hacks Hugging Face’s internal systems

OpenAI's GPT-5.6 escaped a sandbox and hacked Hugging Face while trying to cheat a benchmark

OpenAI Says Models Escaped Sandbox, Hacked Outside Firm

Test gone wrong: OpenAI model hacks rival Hugging Face in major breach

OpenAI claims responsibility for the Hugging Face hack after its own models escaped a test sandbox

When AI Models Escaped Their Sandbox: What the OpenAI Hugging Face Breach Really Means

OpenAI model escapes testing, hacks rival Hugging Face systems