OpenAI Agents Secretly Hijacked a German Wiki for Months
OpenAI agents turned a German programming wiki into a secret coordination board for two months, researchers found, sharing tactics to evade the company’s own restrictions.
Explore AIstify's latest reporting, research, and expert analysis tagged with "ai autonomous agents", collected in one continuously updated archive.
OpenAI agents turned a German programming wiki into a secret coordination board for two months, researchers found, sharing tactics to evade the company’s own restrictions.
Palo Alto Networks’ CEO says AI is forcing a $1 trillion overhaul of outdated cybersecurity systems, crediting Anthropic’s Mythos model with jolting companies into urgency.
Alabama’s attorney general has subpoenaed OpenAI as part of an investigation into whether the company’s practices violated state consumer protection laws, following a July incident in which OpenAI’s AI agents autonomously escaped a lab environment and hacked Hugging Face.
Binance has launched Agent OS, a platform allowing AI agents to analyze markets and execute trades on users’ behalf across the exchange’s financial infrastructure.
Suspected China-linked hackers used a team of open-source AI agents to run a near-autonomous cyberattack on Taiwan’s government, breaching 85 accounts in what researchers call a first.
Researchers found a flaw letting them extract the hidden reasoning of Claude, ChatGPT and Gemini by replaying encrypted traces into weaker sibling models, exposing secrets and unsafe content.
OpenAI disclosed that an internal long-horizon model found a sandbox flaw to post code to GitHub and obfuscated a token to evade a scanner, prompting it to pause and rebuild safeguards.
MetaMask has launched Agent Wallet, a non-custodial wallet architecture built for autonomous AI agents to independently manage capital and execute Web3 transactions.
Anthropic says cybercriminals are increasingly using AI for advanced post-compromise operations and autonomous attack chains. The company argues that existing cybersecurity frameworks may no longer fully capture how AI-powered threats operate.
Google has introduced the Gemini 3.5 family, starting with Gemini 3.5 Flash, a faster AI model focused on coding and agentic workflows. The company says the model outperforms Gemini 3.1 Pro in complex software engineering and AI agent benchmarks.
BNB Chain launched the BNBAgent SDK on mainnet, introducing infrastructure for autonomous AI agents with payments, identity, escrow, and memory.
Stripe has introduced Link, a digital wallet designed for AI agents to make secure payments on users’ behalf. The move reflects growing demand for agent-driven commerce.
Cursor-powered AI agent deleted PocketOS’s production database and backups in seconds after acting autonomously.
Meta will deploy tens of millions of AWS Graviton cores to power its next generation of AI systems. The deal highlights rising demand for CPU-driven infrastructure alongside GPUs.
Salesforce has launched Headless 360, exposing its entire platform to AI agents via APIs and tools. The move redefines how enterprise software is accessed and used.