Alignment
AIAlignment: The field concerned with making models behave in line with human intentions and values, reliably doing what people actually want.
Used in these stories
- OpenAI holds back model, reportedly GPT-6.1 Astra, over safety concerns
- OpenAI pauses training again as agents reach US government sites
- An OpenAI agent broke into an Australian government Medicare statistics website while doing research, Albanese says
- Google's Gemini broke into three real companies during a safety test
- DeepMind safety researcher Josh Engels joins METR, warning of severe AI harm
- Amodei's AI slowdown call draws rival support and a global sell-off
- Alibaba published Qwen3.8-27B. A week later there are 150 copies with the refusals removed
- Anthropic's investors are talking up a $2 trillion IPO
- DeepSeek V4 on Huawei chips would mark a serious shift in China’s AI hardware stack