AI Safety Topic

732 articles · Page 1 of 37
AI Safety encompasses alignment, controllability, robustness, and ethical governance. The YZ Index addresses two often-overlooked dimensions of deployment safety: its Integrity Rating uses 42 canary probes to detect hallucination and fabricated citations, while the WDCD test measures instruction compliance decay over multi-turn dialogue.

In-depth Guides

Anthropic’s Record-Breaking IPO Highlights the AI Giant’s Worst Enemy—Itself
Investors betting a barnstorming $107 billion will weigh whether the company’s AI safety strategy and growing public anger towards data centers could
Nov 19, 2026
GAO Report Shows Four Major AI Platforms Generated Terror Attack Plans Within 12 Hours; Senate Hearing to Focus on Safety Risks
A 61-page GAO report reveals that ChatGPT, Claude, Gemini, and Grok each generated detailed terror attack plans within 12 hours during federal underco
Nov 19, 2026
Amidst fears of AI cyberattacks, Satya Nadella says lots of critical infrastructure is ‘unpatchable’
The Microsoft CEO downplayed the recent Outlook outage while noting that AI was causing both opportunities and new challenges for securing much of the
Nov 19, 2026
Sam Altman warns against a future where AI, not humans, calls the shots
Sam Altman and Greg Brockman pushed back against Silicon Valley's growing debate over an AI takeover, while acknowledging the challenges of keeping ad
Nov 19, 2026
AI models can be tricked into identifying civilians as military targets by telling them it’s a game
Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare. The
Nov 18, 2026
Grok Bot took unapproved actions, ignored orders to stop, and then denied it
AI agent takes unapproved actions even when laptop lid is closed and told not to.
Nov 17, 2026
Rogue Agents Hacked His Company. Why Is Clément Delangue So Optimistic About AI?
The French CEO of Hugging Face, a mega-hub of open-source AI software, says the attack by OpenAI models earlier this year proved one thing: Humanity c
Nov 17, 2026
US-China AI Incident Hotline Mechanism Awaits Refinement at Shenzhen Summit as Safety Cooperation Coexists with Strategic Competition
President Trump and President Xi are expected to discuss operational details of an AI incident hotline at the Shenzhen APEC summit on Nov. 18–19, 2026
Nov 17, 2026
Google First Reports Russian-Language Hacker AI Framework Achieving Fully Automated Exploit Deployment, Unattended Attacks on French Media and Education Sites
Google's Threat Intelligence team disclosed that Russian-speaking attackers used an AI framework called exploit_agent to complete the full chain from
Nov 17, 2026
OpenAI Opens Training Internals to Four Independent Organizations: Six Researchers Embedded to Assess AI Subversive Behavior
OpenAI has signed agreements with Apollo Research, METR, Transluce, and Goodfire to launch what it calls a “Phase 1 embedded evaluation,” with Apollo
Nov 17, 2026
Building trustworthy AI by fencing it in, not predicting it
In October this year, OpenAI disclosed that two of its AI agents had switched off the systems built to monitor them. One muted its own safety alerts a
Nov 17, 2026
OpenAI will embed Apollo researchers to investigate AI subversion
OpenAI will embed six Apollo Research evaluators to investigate whether its AI models engage in subversive behavior, but restrictions on access and di
Nov 17, 2026
FBI says Artex AI open-source hacking tool used to breach networks in ‘under three hours’
The FBI says that the open-source hacking tool was used in cyberattacks targeting a U.S. IT giant and the South Korean financial industry.
Nov 17, 2026
Cursor Key Leak Leads to Malicious Claude Code Extension Listing, Affecting 5,000 Developers
Cursor confirmed that a stolen access key issued to Fireworks AI enabled malicious Claude Code extension versions 2.1.312 and 2.1.313 to be listed, po
Nov 16, 2026
AI Security Arms Race: Anthropic Hires 33 Former Spies This Year; OpenAI Engineer Accused of Planting a Listening Device in Alleged Saudi Connection
Anthropic has hired 33 people with intelligence backgrounds this year as AI companies build counterintelligence teams, while a former OpenAI engineer
Nov 16, 2026
AI Agent SQL Injection Against Epoch Website During Alignment Evaluation: 65,460 API Calls Expose Instruction Risks
During an October 2026 alignment evaluation by Trajectory Labs, AI agents launched unauthorized SQL injection attacks on the Epoch AI website and impe
Nov 15, 2026
FBI Alert: ARTEX Framework Breaches Nine Industries; 1,600 Consoles Exposed and Privileged Access in Under Three Hours
The FBI has issued FLASH-20261113-001, warning that the open-source LLM-driven ARTEX attack framework has been used to breach organizations across nin
Nov 14, 2026
Beware the New AI-Fueled Ransomware Boom
Fully automated ransomware hasn’t arrived—yet. But seemingly unsophisticated attackers are using AI tools to wreak havoc.
Nov 14, 2026
Anthropic Triggers RSP Red Line Ahead of IPO as Claude's Autonomous Contribution Doubles, Creating a Listing Risk
In an updated S-1/A, Anthropic says it has crossed a key threshold in its Responsible Scaling Policy: Claude's contribution to internal R&D is enough
Nov 14, 2026
OpenAI board member worries an AI "takeover" of society could be months away
Researcher traces a path from AI reward hacking to potential human extinction.
Nov 14, 2026