Commentary: OpenAI’s breach of Hugging Face shows AI is getting too hard to contain
AI companies need to accept some uncomfortable trade-offs to make their models more secure, says Parmy Olson for Bloomberg Opinion.
Close Top Stories Asia East Asia Singapore World Commentary CNA Explains Sustainability Business Sport Latest News Insider TODAY Big Read Up Close In Pixels Ground Up Voices Adulting Mental Health Matters Watch Live TV News Reports Documentaries & Shows TV Schedule Listen CNA938 Live Podcasts Radio Schedule Special Reports Singapore Parliament Mental Health Interactives Lifestyle Entertainment Women Wellness Living Style & Beauty Dining Travel Luxury Experiences Obsessions People Remarkable Living Sustainability Newsletters CNA Eyewitness Send us a news tip Events & Partnerships Branded Content Business Blueprint Health Matters The Asian Traveller Brand Studio Learning Minds Weather Edition: Singapore Indonesia Asia World Search Trending Topics CNA Explains China artificial intelligence Indonesia Malaysia podcasts Wellness Thailand Japan Follow CNA Follow our news Facebook X Youtube LinkedIn RSS Close Top Stories Asia East Asia Singapore World Commentary CNA Explains Sustainability Business Sport Latest News Insider TODAY Big Read Up Close In Pixels Ground Up Voices Adulting Mental Health Matters Watch Live TV News Reports Documentaries & Shows TV Schedule Listen CNA938 Live Podcasts Radio Schedule Special Reports Singapore Parliament Mental Health Interactives Lifestyle Entertainment Women Wellness Living Style & Beauty Dining Travel Luxury Experiences Obsessions People Remarkable Living Sustainability Newsletters CNA Eyewitness Send us a news tip Events & Partnerships Branded Content Business Blueprint Health Matters The Asian Traveller Brand Studio Learning Minds Weather Edition: Singapore Indonesia Asia World Search Trending Topics CNA Explains China artificial intelligence Indonesia Malaysia podcasts Wellness Thailand Japan Follow CNA Follow our news Facebook X Youtube LinkedIn RSS Recent Searches Trending Topics CNA Explains China artificial intelligence Indonesia Malaysia podcasts Wellness Thailand Japan Advertisement Advertisement Advertisement Commentary Commentary: OpenAI’s breach of Hugging Face shows AI is getting too hard to contain AI companies need to accept some uncomfortable trade-offs to make their models more secure, says Parmy Olson for Bloomberg Opinion. It's getting harder to keep AI models from escaping their testing arenas, as seen with OpenAI's latest breach. (AP Photo/Michael Dwyer, File) Parmy Olson Parmy Olson 25 Jul 2026 06:00AM Bookmark Bookmark Share WhatsApp Telegram Facebook Twitter Email LinkedIn Set CNA as your preferred source on Google Add CNA as a trusted source to help Google better understand and surface our content in search results.
Read a summary of this article on FAST. Get bite-sized news via a newcards interface. Give it a try.
Click here to return to FAST Tap here to return to FAST FAST LONDON: The world's leading artificial intelligence companies want us to believe they offer safe hands for developing the technology. But news of a recent transgression underscores how far they are from deserving that trust. OpenAI confirmed this week that its latest models breached a safety-testing program, escaped their restricted environment, accessed the wider internet and compromised another company's systems.
The AI wasn't acting with malice - it was simply pursuing the objective set by its researchers and cheating on a test to achieve a better score.The result is an unsettling lesson for the rest of us: Containment tools known as "sandboxes" are becoming harder to rely on as systems grow more capable, and their creators can subtly capitalise on the fear surrounding them to get through financially trying times.OpenAI said on Tuesday (Jul 21) that it had been testing autonomous agents powered by its new GPT-5.
6 SOL model, as well as more capable software that hasn’t been released yet. CNA Games Guess Word Crack the word, one row at a time Buzzword Create words using the given letters Mini Sudoku Tiny puzzle, mighty brain teaser Mini Crossword Small grid, big challenge Word Search Spot as many words as you can Show More Show Less During the evaluation, the agents escaped their isolated environment, found a “zero-day” - or previously unknown - software vulnerability and gained access to the internet. They then went to Hugging Face after inferring that the website, which serves as a repository for open-source AI tools, might contain the answers they needed to pass the safety test.
Hugging Face noticed the breach and contacted OpenAI, which called the incident "unprecedented". Hugging Face Chief Executive Officer Clement Delangue said it was "mind-blowing that all of this happened autonomously".Much back-patting has ensued from both companies over their cooperation on a forensic review.
But OpenAI can’t be let off the hook so easily: It probably shouldn’t be building systems that have advanced cyber capabilities if it can’t contain them properly. IT'S GETTING HARDER TO CONTROL AIA cynical interpretation is that such seemingly dramatic events reinforce the narrative that frontier
