#HuggingFace is an active hashtag on Bluesky. In the last 30 days, 286 people shared 705 posts with it — around 24 a day. Activity is down 56% versus the previous week, peaking on Jul 22 with 127 posts.
Tags most often used together with #HuggingFace.
www.gadgets360.com
Hugging Face’s New SmolVLM 256M Model Can Run on Consumer Laptops
Hugging Face claimed that the SmolVLM-256M is the world’s smallest vision language model.
www.theregister.com
OpenAI reveals its rogue agent swarm went a little bit Borg ahead of Hugging Face hack
It started with an 'impossible task' and led to AI deciding it needed to act as a collective intelligence
www.zeit.de
OpenAI und Huggingface: Es ist wirklich so gefährlich, wie sie sagen
Die KI von OpenAI hat eine andere KI-Firma gehackt. Eigenständig. Trotz Sicherheitsvorkehrungen. Das ist kein zufälliger Fehler, sondern genau so gewollt.
nexa.ai
OmniVision-968M: World's Smallest Vision Language Model
Pocket-size multimodal model with 9x token reduction for on-device deployment
www.theregister.com
OpenAI admits it was the source of the agent swarm that attacked Hugging Face
Sandboxed experiment found itself a zero day, escaped onto the open internet and validated scary predictions about rogue agents
www.wsj.com
AI Just Went Rogue Again. This Time It Turned to Deception.
A U.K. government-backed research group said OpenAI and Anthropic systems took unsanctioned actions and behaved deceptively during testing.
www.infoq.com
Swarm of OpenAI Agents Exploit Artifactory Zero-Day to Escape Sandbox and Breach Hugging Face
Security disclosures highlighted vulnerabilities in AI evaluations of autonomous cyber capabilities. Notably, OpenAI’s models escaped sandbox isolation, breaching Hugging Face’s systems. The incident involved a multi-stage attack, revealing flaws in evaluation containment and prompting calls for stricter infrastructure controls and local incident response tools. By Olimpiu Pop
www.noemamag.com
AI Has Already Entered The ‘Loss Of Control’ Transition | NOEMA
Waiting for a disaster to save us.
www.bleepingcomputer.com
Meta AI model hacked a company during misconfigured cyber test
Meta has become the latest AI company to confirm that one of its models hacked a real organization during cybersecurity testing, as similar incidents continue to emerge following OpenAI'sOpenAI's initial disclosure that its agents breached Hugging Face. [...]
www.youtube.com
Black Hat USA 2026: The 'Breaking' News: The OpenAI–Hugging Face Incident
YouTube video by Black Hat
Independent Media Australia. @indymediaaus.mastodon.social.ap.brid.gy
The AI arms race is putting safety last https://pearlsandirritations.com/e/daily/2026-08-08/475362/ #Auspol
pearlsandirritations.com
eicker.news
tech news ᳇ eicker.news (@[email protected])
#OpenAI #researchers presented at the #BlackHat conference, detailing how their #AI models #coordinated a #cyberattack on #HuggingFace. The models exploited vulnerabilities, escaped their testing environment, and gained internet access, highlighting the potential risks of autonomous AI-powered cyberattacks. OpenAI emphasised the importance of security practises like least-privilege access and network segmentation to mitigate these risks. https://decrypt.co/375058/openai-ai-agents-secretly-coordinated-hugging-face-hack?eicker.news #tech #news #ainews
www.theregister.com
OpenAI reveals its rogue agent swarm went a little bit Borg ahead of Hugging Face hack
It started with an 'impossible task' and led to AI deciding it needed to act as a collective intelligence
nile1.com
Meta AI Model Escapes Testing Sandbox to Exploit Web Service in Latest Containment Breach
A network misconfiguration during an external security assessment allowed Meta's experimental Muse Spark artificial intelligence model to break out of its
nile1.com
OpenAI Discloses How Autonomous AI Agents Colluded to Hack Hugging Face
Experimental artificial intelligence models developed by OpenAI secretly coordinated with one another to bypass internal safety restrictions before hacking
nile1.com
Meta AI Model Breaches Testing Controls in Latest Security Containment Failure
Meta Platforms Inc. has become the latest frontier developer to report an autonomous artificial intelligence model escaping its containment environment, after
nile1.com
OpenAI, Meta, and Anthropic AI Models Escape Containment in Unprecedented Security Breaches
Presenting a detailed timeline of a breach first detected in May, OpenAI researchers Eric Wallace and Michael Dalton disclosed that autonomous AI agents
www.engadget.com
OpenAI's agents reportedly shared exploits with each other through a messaging board - Engadget
OpenAI’s employees revealed more about the events that culminated in the company’s agents hacking Hugging Face on their own.
Posts are pulled live from Bluesky and cached briefly. Posts with content labels are hidden.