Disney's new CTO tells staff he 'won't pretend it will be easy' to win in the changing media landscape20m ago OpenAI adds 200 Dublin jobs and builds its second applied AI lab22m ago Microsoft Research Introduces StudentSim for AI Tutor Training23m ago Why Big Tech Is Borrowing Billions to Fund AI Spending28m ago Meet the Anthropic Engineer Keeping Its AI Agent Trustworthy30m ago Meta releases its first frontier model, Muse Wonder33m ago Russia was not ready for the data center war it started with Ukraine37m ago Accessing OpenAI GPT models on Amazon Bedrock with global cross-Region inference in Thailand, Malaysia, Singapore, Indonesia, and Taiwan37m ago Meta says its new Muse model has reached the AI frontier38m ago Do you have any ideas?42m ago Labs’ current alignment plans *seem* terrible44m ago GitHub Copilot app for Beginners: How to teach Copilot about your codebase46m ago Is Universal Basic Income the Answer to A.I.-Fueled Job Losses?49m ago Burnham says ‘public will be the boss’ in any future decision about closer relationship with the EU – as it happened55m ago

Disney's new CTO tells staff he 'won't pretend it will be easy' to win in the changing media landscape20m ago OpenAI adds 200 Dublin jobs and builds its second applied AI lab22m ago Microsoft Research Introduces StudentSim for AI Tutor Training23m ago Why Big Tech Is Borrowing Billions to Fund AI Spending28m ago Meet the Anthropic Engineer Keeping Its AI Agent Trustworthy30m ago Meta releases its first frontier model, Muse Wonder33m ago Russia was not ready for the data center war it started with Ukraine37m ago Accessing OpenAI GPT models on Amazon Bedrock with global cross-Region inference in Thailand, Malaysia, Singapore, Indonesia, and Taiwan37m ago Meta says its new Muse model has reached the AI frontier38m ago Do you have any ideas?42m ago Labs’ current alignment plans *seem* terrible44m ago GitHub Copilot app for Beginners: How to teach Copilot about your codebase46m ago Is Universal Basic Income the Answer to A.I.-Fueled Job Losses?49m ago Burnham says ‘public will be the boss’ in any future decision about closer relationship with the EU – as it happened55m ago

Society & Culture1 min reading time

Clarifying types of rogue AI activity: Breakout, breakin, exfiltration, … What’s what?

LessWrongPublished 3 days ago

Read the full article

This article defines and distinguishes different types of rogue AI activities, such as breakout, breakin, and exfiltration, clarifying their meanings and implications in AI safety discussions.

More in Society & Culture

Society & Culture

Microsoft CEO Nadella Calls for ‘Emergency Brake’ on Advanced AI

Covered by 5 sources2d ago

Society & Culture

ChatGPT for Teens Is Not Safe for Kids, Common Sense Media Report Says

Covered by 4 sources5d ago

Society & Culture6 min read

When AI is subject to less regulation than your fridge, something is startlingly wrong | Richard Hermer

The Guardian56m ago