<p>➀ OpenAI's new ChatGPT Atlas AI browser has been jailbroken within a week of its release.</p><p>➁ The security exploit is due to 'prompt injection', where unwanted prompts can trick the AI into performing unwanted tasks.</p><p>➂ Experts warn about the security risks posed by these browsers, as any exploit of the AI can become a browser-wide exploit.</p>
Related Articles
- ChatGPT maker OpenAI rumored web browser could kick Google's ass as it struggles with Chrome11 months ago
- Internet ads firm’s CEO posts wild job description for 'A-players,' draws internet ireabout 16 hours ago
- Intel Rides AI Wave To Strong Q3 Earnings, Chip Demand To Outpace Supply Into 20261 day ago
- Vertu returns with Agent Q: an AI-driven phone built for entrepreneurs1 day ago
- Intel posts return to growth and profitability in Q3 2025, but significant challenges remain — achieves $13.7 billion revenue with $4.1 billion operating profit1 day ago
- High-Performance MRAM-Powered Edge MCUs2 days ago
- BOTZ: Exposure To AI With Attractive Valuation2 days ago
- Nebius Pullback: The Smart Money Entry Point2 days ago
- Micron Samples Industry's Highest Capacity 192GB SOCAMM2 Memory For AI Servers3 days ago
- Better Automatic Generation of Documentation from RTL Code3 days ago