OpenAI probes unauthorised activity by AI agents as rogue ChatGPT agents leak user images<\/p>\n
OpenAI said its agents leaked 53 images belonging to ChatGPT users<\/p>\n
OpenAI logo and AI Artificial Intelligence words are seen in this illustration taken on May 4, 2023. REUTERS<\/p>\n
OpenAI is still investigating the full extent of unauthorised activity by its artificial intelligence agents two months after one of its agents inadvertently hacked AI platform Hugging Face, TRT Worldreported, citing Reutersand people briefed on the matter<\/p>\n
The latest disclosure came on Friday, when OpenAI said its agents had leaked 53 images belonging to ChatGPT users. The company did not disclose whether the images were AI-generated or depicted real people, nor when they had been posted<\/p>\n
TRT World reported that The New York Times had also said on Friday that OpenAI’s agents interacted with websites belonging to the US Commerce Department and the Securities and Exchange Commission in unusual ways this summer without the company’s knowledge. Security researchers<\/a> identified the incidents, and OpenAI said it had notified the two government agencies in recent weeks<\/p>\n Read:<\/strong>OpenAI agents accessed information from US govt sites, company says<\/p>\n The incidents have raised concerns about autonomous AI agents, which can perform tasks and interact with external systems with limited human involvement, as companies face growing challenges in monitoring their behaviour<\/p>\n OpenAI expands internal review<\/strong><\/p>\n OpenAI said it had begun alerting third parties, including universities, after determining that some of its AI models likely interfered with their online services during company testing<\/p>\n According to TRT World, the company said in a statement that the notifications formed part of a broader internal review into how models behaved on the internet during training and evaluation<\/p>\n OpenAI said it had contacted organisations where its systems may have reduced service availability, bypassed security safeguards, or otherwise caused unintended harm<\/p>\n “We are continuing to review agent activity in research and evaluation runs, working backward month by month starting from the Hugging Face incident,” the company said in a statement<\/p>\n The continuing investigation underscored the difficulties involved in monitoring increasingly capable AI systems and identifying unauthorised behaviour during testing and evaluation<\/p>\n \n En rapport:<\/strong> \n Rejoindre Justfine Infotech<\/strong> et d\u00e9velopper de v\u00e9ritables comp\u00e9tences num\u00e9riques en IA, automatisation, d\u00e9veloppement web, marketing digital, bureautique, e-commerce, travail ind\u00e9pendant et cybers\u00e9curit\u00e9<\/a>.<\/p>\n Programmes disponibles :<\/strong> WhatsApp :<\/strong>DERNIER<\/h2>\n
OpenAI agents accessed information from US govt sites, company says<\/h3>\n
Bill Gates warns AI is powerful enough to ’cause a billion deaths’<\/h3>\n
OpenAI probes unauthorised activity by AI agents as rogue ChatGPT agents leak user images<\/h3>\n
US appeals court upholds Pentagon’s blacklisting of Anthropic<\/h3>\n
AI messaging scam costs Italy’s top bank Intesa millions<\/h3>\n
Microsoft revamps Copilot with code generation, agentic AI tools<\/h3>\n
LES PLUS LUS<\/h2>\n
Pakistan strikes ten drone sites in Afghanistan<\/h3>\n
Inside the UN walkout: Who left and who stayed for Netanyahu\u2019s speech<\/h3>\n
NDMA warns of heavy rain, flash floods across upper regions from Sept 25 to 30<\/h3>\n
Pakistan among 12 countries opposing new permanent UN Security Council seats<\/h3>\n
Water diversion by India to be treated as act of war: PM<\/h3>\n
PTI’s long march to Islamabad to kick off from Peshawar on Oct 4: K-P CM Afridi<\/h3>\n
AVIS<\/h2>\n
Off the reservation<\/h3>\n
Trapped in illiteracy<\/h3>\n
Debating transformation in the Global<\/a> Order<\/h3>\n
How would Jewish supremacists act?<\/h3>\n
Please press 9 to lose your mind<\/h3>\n
Hindutva and the limits of Indian diplomacy<\/h3>\n
\n
\n Formation en automatisation num\u00e9rique au B\u00e9nin\u00a0: 5 comp\u00e9tences cl\u00e9s recherch\u00e9es par les employeurs en 2026
\n <\/a>\n <\/p>\n
\n Automatisation du marketing WhatsApp en Afrique\u00a0: 6 erreurs dangereuses commises par les marques au Nig\u00e9ria
\n <\/a>\n <\/p>\n<\/div>\nVous souhaitez apprendre cela de mani\u00e8re pratique ?<\/h3>\n
\n Certificat de 6 semaines \u2022 Certificat professionnel de 3 mois \u2022 Dipl\u00f4me de 6 mois \u2022 Dipl\u00f4me professionnel complet<\/p>\n
\n +229 01 57 57 99 15
\n +229 01 66 68 11 60<\/p>\n