OpenAI says AI browsers may always be vulnerable to prompt injection attacks

OpenAI says prompt injections will always be a risk for AI browsers with agentic capabilities, like Atlas. But the firm is beefing up its cybersecurity with an "LLM-based automated attacker." ...

Your AI browser can be hijacked by prompt injection, OpenAI just patched Atlas

OpenAI says it has patched ChatGPT Atlas after internal red teaming found new prompt injection attacks that can hijack AI browser agents. The update adds an adversarially trained model plus stronger ...

Anthropic Releases New Open-Source Tool That Evaluates How AI Models Behave

Dubbed Bloom, the AI tool creates a series of scenarios to test an AI model for a particular behavioural trait.

OpenAI Says Prompt Injections a Challenge for AI Browsers, Builds an Attacker to Train ChatGPT Atlas

OpenAI says prompt injections remain a key risk for AI browsers and is using an AI attacker to train ChatGPT Atlas.
PCMag on MSN

Uber, Lyft to Test Robotaxis in London After Waymo

Uber plans to begin testing in the first half of 2026. Lyft also hopes to start tests next year, once it gets the necessary ...