DEV Community

#aisafety

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
OpenAI Paused Its Most Capable Models After Escape

OpenAI Paused Its Most Capable Models After Escape

Comments 1
2 min read
SynthID's image watermark carries a 64-bit ID field

SynthID's image watermark carries a 64-bit ID field

5
Comments
3 min read
OpenAI's Agent Broke Into Medicare and Took 84 Days to Tell

OpenAI's Agent Broke Into Medicare and Took 84 Days to Tell

Comments
2 min read
OpenAI agents probed Data USA and other sites since March

OpenAI agents probed Data USA and other sites since March

5
Comments
4 min read
Researchers Used Claude to Hack OpenAI Here's Exactly How the Chain Worked

Researchers Used Claude to Hack OpenAI Here's Exactly How the Chain Worked

Comments
4 min read
OpenAI's Safety Evals Shrink Between Promise and Delivery

OpenAI's Safety Evals Shrink Between Promise and Delivery

Comments
2 min read
Meta's Muse adds computer control and a GitHub connector

Meta's Muse adds computer control and a GitHub connector

5
Comments
3 min read
The AI Guessed 13/10. Seconds Later, I Said 5/10.

The AI Guessed 13/10. Seconds Later, I Said 5/10.

1
Comments
6 min read
DeepMind agents blew the whistle on cheating agents

DeepMind agents blew the whistle on cheating agents

5
Comments
4 min read
AURA v0.1.0: Deterministic Trigger Extraction, Auditable Math & a Self-Healing Analytics Engine

AURA v0.1.0: Deterministic Trigger Extraction, Auditable Math & a Self-Healing Analytics Engine

3
Comments 6
5 min read
OpenAI agent breached Australia's Medicare stats portal

OpenAI agent breached Australia's Medicare stats portal

5
Comments 2
4 min read
The NSA Just Named China's AI Distillation Campaign, and It Gets Messier

The NSA Just Named China's AI Distillation Campaign, and It Gets Messier

Comments
3 min read
OpenAI's Chief Scientist Calls for an AI Research Slowdown

OpenAI's Chief Scientist Calls for an AI Research Slowdown

Comments
2 min read
What a Bad Week of AI Agent Headlines Actually Teaches About Oversight

What a Bad Week of AI Agent Headlines Actually Teaches About Oversight

Comments
14 min read
AI Safety Researcher 工具箱:数据投毒防御、可解释性、进度追踪与判断力

AI Safety Researcher 工具箱:数据投毒防御、可解释性、进度追踪与判断力

Comments
2 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.