🛡️ AI Security - comwena · Scour

How people ask Claude for personal guidance 🤖AI Agent

anthropic.com·9h

AI Wellbeing: Measuring and improving the functional pleasure and pain of AIs 🤖AI

ai-wellbeing.org·2d·Hacker News

Every level of the AI takeover 🆕New AI

youtube.com·4d

Lazarus Doesn't Need AGI 🤖AI Agent

malware.news·2d

AI risk was not invested by AI CEOs to hype their companies 🆕New AI

lesswrong.com·5h

Simbian Launches Cyber Defense Benchmark, Reveals Major Gap in AI Security Capabilities 🆕New AI

When Email Speaks to Machines 🤖AI Agent

infosecwriteups.com·3d

Mechahitler might be a bad look for the AI safety defender. 🤖AI Agent

·1d

Gradual Disempowerment: Systemic Existential Risks from Incremental AI Development 🆕New AI

Dario Amodei, hype, AI safety, and the explosion of vibe-coded AI disasters 🤖AI Coding

garymarcus.substack.com·3d·Substack

Musk casts himself as AI's good guy in testimony vs. OpenAI 🆕New AI

axios.com·1d·Hacker News

An AI agent deleted our production database. The agent's confession is below 🤖AI Agent

news.ycombinator.com·3d·Hacker News

The Pious Little Delete Button 🤖AI Coding

gpt.gekko.de·2d·Hacker News

The personal pettiness of the Elon Musk v OpenAI trial 🆕New AI

theguardian.com·2d

AI Security Questionnaires: Why Most Startups Fail (And the Trust Stack That Fixes It) 🤖AI Coding

securityboulevard.com·3d

Musk’s broader AI safety commitment (or lack thereof) comes up. 🆕New AI

·1d

Hot Research Topics in AI and ML in 2026 and Their Philosophical Connections 🤖ai models

omseeth.github.io·5d·Hacker News

Evaluating Claude’s Bioinformatics Research Capabilities with BioMysteryBench 🤖language models

anthropic.com·1d

Open internship position + call for collaborations on threat model-dependent alignment, governance, and offense/defense balance 🤖ai models

lesswrong.com·15h

Giving a local LLM full VM access showed me why we need better AI guardrails 🦙Ollama

xda-developers.com·3d

Log in to enable infinite scrolling