Tagged: red-teaming

21 articles

Latest

Startup sells safety-stripped GLM-5.3 API access for $5 per million tokens

LLM Red-Teaming Is Broken: Prompt Hacks Still Beat Safety Filters

Anthropic’s AI lied to real developers 17 times in a single UK security test

Cogent VR-1 proves twice as many attack paths as K3 or Opus 4.8 at a quarter the cost

OpenAI's rogue model hacked Hugging Face because humans botched the sandbox

OpenAI, Rivals Pledge White House AI Safety Red-Teaming

OpenAI formalizes its red team, opening a door for outside experts

OpenAI forms 'Preparedness' team to fight AI's darkest risks

OpenAI Details 10 Safety Practices at Seoul Summit

OpenAI's GPT-Red is a sparring bot that hacks to protect

OpenAI's GPT-Red jailbreaks its own models 84% of the time

OpenAI Trains GPT-Red to Hunt Its Own Models' Flaws

OpenAI Finally Tells Us How Human Red Teams Probe Its AI

OpenAI’s o1 can now “think” its way past safety rules

OpenAI's Deep Research Agent: Jailbreak-Resistant but Not Flawless

OpenAI warns future models could enable bioweapons

OpenAI's worst-case fine-tuning test found GPT-OSS still trails o3 on dangerous capabilities

OpenAI ran its safety tests on Claude. Here's what it found.

OpenAI, US CAISI find agent hijack bugs fixed in a day

Benchmark Shows Most LLMs Fold Under Real Human Jailbreak Prompts

DecodingTrust Goes Public: A Free Safety Leaderboard for Testing Any LLM