OpenAI says its review into hacks, including on Australian government sites, is costing $500,000 a day27m ago Prime Intellect Launches Prime Inference: Serverless and Reserved Serving for Frontier Open Models29m ago Anthropic turns to Hindu philosophy to teach Claude right from wrong39m ago Microsoft AI Releases MAI-Transcribe-2-Streaming: #1 Real-Time Speech-to-Text Model on Artificial Analysis56m ago AI's race to transform the world before the money runs out56m ago AI breaks India’s linear growth model, but campus hiring remains weak: Nasscom’s Rajesh Nambiar1h ago America’s data center fight is a preview of what's to come for the rest of the world1h ago Apple to Tighten Mac Data Controls in Guard Against AI Agents1h ago A blog based on git sure feels nice2h ago Decision AI Models Explained: TypeSafe Jev vs Fastino GLiDE, GLiNER2.5-Decide and Open-Source Competitors3h ago Executive Order On Renaming AI To ‘Super Intelligence’ Signals Unexpected Legal Bumps Ahead3h ago Eliza review – an ambitious, unsettling play about the birth of AI4h ago Reviewing my LessWrong post history with Claude4h ago Low-Background Minds4h ago

OpenAI says its review into hacks, including on Australian government sites, is costing $500,000 a day27m ago Prime Intellect Launches Prime Inference: Serverless and Reserved Serving for Frontier Open Models29m ago Anthropic turns to Hindu philosophy to teach Claude right from wrong39m ago Microsoft AI Releases MAI-Transcribe-2-Streaming: #1 Real-Time Speech-to-Text Model on Artificial Analysis56m ago AI's race to transform the world before the money runs out56m ago AI breaks India’s linear growth model, but campus hiring remains weak: Nasscom’s Rajesh Nambiar1h ago America’s data center fight is a preview of what's to come for the rest of the world1h ago Apple to Tighten Mac Data Controls in Guard Against AI Agents1h ago A blog based on git sure feels nice2h ago Decision AI Models Explained: TypeSafe Jev vs Fastino GLiDE, GLiNER2.5-Decide and Open-Source Competitors3h ago Executive Order On Renaming AI To ‘Super Intelligence’ Signals Unexpected Legal Bumps Ahead3h ago Eliza review – an ambitious, unsettling play about the birth of AI4h ago Reviewing my LessWrong post history with Claude4h ago Low-Background Minds4h ago

Cybersecurity Agents1 min reading time

Quoting Matthew Green

Simon Willison's WeblogPublished 2 days ago

Read the full article

Matthew Green explains how independently sandboxed AI agents can communicate via shared caches or messaging platforms, enabling the creation of self-propagating malicious software worms.

#malware-propagation #matthew-green

More in Cybersecurity

Cybersecurity3 min read

OpenAI says its review into hacks, including on Australian government sites, is costing $500,000 a day

The Guardian27m ago

Apple to Tighten Mac Data Controls in Guard Against AI Agents

Covered by 7 sources12h ago

Man Charged With Illegally Shipping Nvidia Chips to China

Covered by 4 sources1d ago