🛡️ AI Safety Evals - buckman · Scour

Iliad is Hiring

🧠Rationality

lesswrong.com·

Less-relevant results

Microsoft updates AI agent security taxonomy with seven new failure modes

Autonomous Pentesting vs Autonomous Red Teaming: What's the Difference?

Securing AI Systems: Red Teaming, Prompt Injection, and Adversarial Testing

🛡️LLM Security Blog

Controversial smut as an AI alignment issue

⚖️Ethics News Blog

thingofthings.substack.com··Substack

Latest technical articles & videos.

🤖Large Language Models

certdepot.net·

Sam Altman said automating everything will be 'unfulfilling' and 'dangerous'

🎭Anthropic Claude News

businessinsider.com

·

Neglected Basics of AI Alignment

🛡️LLM Security

lesswrong.com·

Infosecurity Europe: Practical Lessons From Lloyds' Agentic AI Security Playbook

🎯Agentic AI Red Teaming News

infosecurity-magazine.com·

Meta’s AI Support Hack Is a Warning for Every Team Automating User Access

🕳LLM Vulnerabilities Discussion

langprotect.com··DEV

Solstice Sync: A Dynamic Gemini AI Alignment Puzzle

⚖️Ethics Blog

Anthropic Urges Global Pause in AI Development, Flags 'Self-Improvement' Risk

🎭Anthropic Claude

Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

AI Security Tools: May 2026

🔓Vulnerability Research Blog

·

On Slop

🎯Pen Testing

lesswrong.com·

An Anthropic employee's 2-sentence quote crystallizes the state of AI confusion at work

🎭Anthropic Claude News

businessinsider.com

·

Learnings from starting an AI safety research team

🛡️AI Safety

lesswrong.com·

Anthropic proposes global development pause to mitigate recursive AI risks

🎭Anthropic Claude

Book of Cron Job

🐚Shell Scripting

lesswrong.com·

Is it unethical to work on robotics capabilities research?

🚀Frontier AI

lesswrong.com·

No more posts from buckman's subscribed feeds.

Scour all 25255 feeds Learn more about Feeds

Log in to enable infinite scrolling