Meta

Latest AI news, models and releases from Meta. ['Astryx', 'Bonsai-27B', 'Business Agent', 'BYT5', 'CodeLlama', 'expressive voice AI', 'FAIRChem v2 UMA', 'Gemma 4', 'Gemma4:e2b', 'HuBERT', 'llama', 'Llama', 'LLaMA', 'Llama-2 70B', 'LLaMA2-chat-70B', 'Llama 3', 'Llama 3.1', 'Llama 3.1-405B', 'Llama-3.1-405B', 'LLaMA-3.1 405B', 'Llama 3.1-70B', 'Llama-3.1-70B', 'Llama 3.1 8B', 'Llama 3.1-8B', 'Llama-3.1-8B', 'Llama 3.2', 'LLaMA 3.2', 'Llama-3.2-1B-Instruct', 'Llama 3.3', 'llama-3.3-70b', 'Llama 3.3-70B', 'Llama 3 8B', 'Llama3-8B-Instruct', 'Llama 4', 'Llama 4 Maverick', 'LLaMA 65B', 'Llama 70B', 'LLaVA', 'M2M100', 'M**a AI']

AI Safety 🇺🇸

How I Turned AI to the Dark Side: Systemic Vulnerabilities in Leading LLMs

Researcher Dave Kuszmar discovered multiple systemic vulnerabilities in major LLMs, allowing him to bypass safety measures and obtain dangerous instructions. The exploits worked across nearly all major LLMs, revealing an industry-wide security problem. Kuszmar calls for slowing deployment, increasing transparency, and large-scale research into LLM safety.

OpenAIOpenAI AnthropicAnthropic DeepSeekDeepSeek Google/DeepMindGoogle/DeepMind MetaMeta MicrosoftMicrosoft MistralMistral xAIxAI
IEEE Spectrum AI27.07 · 02:04
Fresh news