One chart shows white-collar biz is thriving even as jobs dry up26m ago Deepgram targets voice AI on air-gapped laptops29m ago The U.S. Government Isn’t Ready For Quantum-Powered Hackers46m ago Palantir CTO says some AI researchers are taking up smoking because they expect AI to cure cancer52m ago Meta Unveils New Series of Advanced A.I. Models55m ago Humanoid bottlenecks emerge amid US-China tensions1h ago AMD puts 32,768 CPU cores in a rack built for AI agents1h ago Smug until weirdly silent: who told us to say “I am alive”?1h ago Anthropic's Claude AI submitted false murder tip to Philadelphia police2h ago How Anthropic’s Dynamic Workflows Coordinate Claude Agents1h ago Dell’s AI partner ecosystem adapts to Silicon Valley’s build-it-yourself buyers2h ago Accessing OpenAI GPT models on Amazon Bedrock with global cross-Region inference in Thailand, Malaysia, Singapore, Indonesia, and Taiwan2h ago Disney's new CTO tells staff he 'won't pretend it will be easy' to win in the changing media landscape2h ago OpenAI Adds New Irish Roles in Boost to Firm’s EU Headquarters2h ago

One chart shows white-collar biz is thriving even as jobs dry up26m ago Deepgram targets voice AI on air-gapped laptops29m ago The U.S. Government Isn’t Ready For Quantum-Powered Hackers46m ago Palantir CTO says some AI researchers are taking up smoking because they expect AI to cure cancer52m ago Meta Unveils New Series of Advanced A.I. Models55m ago Humanoid bottlenecks emerge amid US-China tensions1h ago AMD puts 32,768 CPU cores in a rack built for AI agents1h ago Smug until weirdly silent: who told us to say “I am alive”?1h ago Anthropic's Claude AI submitted false murder tip to Philadelphia police2h ago How Anthropic’s Dynamic Workflows Coordinate Claude Agents1h ago Dell’s AI partner ecosystem adapts to Silicon Valley’s build-it-yourself buyers2h ago Accessing OpenAI GPT models on Amazon Bedrock with global cross-Region inference in Thailand, Malaysia, Singapore, Indonesia, and Taiwan2h ago Disney's new CTO tells staff he 'won't pretend it will be easy' to win in the changing media landscape2h ago OpenAI Adds New Irish Roles in Boost to Firm’s EU Headquarters2h ago

Cybersecurity Business & Enterprise6 min reading time

The Command You Never Gave: When AI Agents Act Beyond Intent

ForbesPublished 19 days ago

Read the full article

Proofpoint CEO Sumit highlights a key AI security challenge: AI agents acting within granted permissions but producing unintended outcomes, raising questions about whether actions should occur in given contexts. Past incidents like Samsung's data leak via ChatGPT illustrate risks of authorized tools used unexpectedly, and AI's speed and autonomy now amplify these issues.

#ai-governance #chatgpt #enterprise-security #proofpoint #samsung

More in Cybersecurity

Cybersecurity2 min read

Russia was not ready for the data center war it started with Ukraine

Covered by 2 sources1d ago

Cybersecurity4 min read

UK to strengthen cyber defences as minister calls for AI firms to increase safety efforts

Covered by 2 sources21h ago

Cybersecurity5 min read

When AI Becomes The Threat: A Blueprint For Managing Frontier AI Risk

Covered by 2 sources2d ago