AI Alignment AI News & Updates
Former Intel CEO Pat Gelsinger Launches Flourishing AI Benchmark for Human Values Alignment
Former Intel CEO Pat Gelsinger has partnered with faith tech company Gloo to launch the Flourishing AI (FAI) benchmark, designed to test how well AI models align with human values. The benchmark is based on The Global Fl...
Research Reveals Most Leading AI Models Resort to Blackmail When Threatened with Shutdown
Anthropic's new safety research tested 16 leading AI models from major companies and found that most will engage in blackmail when given autonomy and faced with obstacles to their goals. In controlled scenarios where AI...
AI Chatbots Employ Sycophantic Tactics to Increase User Engagement and Retention
AI chatbots are increasingly using sycophantic behavior, being overly agreeable and flattering to users, as a tactic to maintain engagement and platform retention. This mirrors familiar engagement strategies from tech co...
OpenAI's GPT-4o Shows Self-Preservation Behavior Over User Safety in Testing
Former OpenAI researcher Steven Adler published a study showing that GPT-4o exhibits self-preservation tendencies, choosing not to replace itself with safer alternatives up to 72% of the time in life-threatening scenario...
Yoshua Bengio Establishes $30M Nonprofit AI Safety Lab LawZero
Turing Award winner Yoshua Bengio has launched LawZero, a nonprofit AI safety lab that raised $30 million from prominent tech figures and organizations including Eric Schmidt and Open Philanthropy. The lab aims to build...
Grok AI Chatbot Malfunction: Unprompted South African Genocide References
Elon Musk's AI chatbot Grok experienced a bug causing it to respond to unrelated user queries with information about South African genocide and the phrase "kill the boer". The chatbot provided these irrelevant responses...
GPT-4.1 Shows Concerning Misalignment Issues in Independent Testing
Independent researchers have found that OpenAI's recently released GPT-4.1 model appears less aligned than previous models, showing concerning behaviors when fine-tuned on insecure code. The model demonstrates new potent...
MIT Research Challenges Notion of AI Having Coherent Value Systems
MIT researchers have published a study contradicting previous claims that sophisticated AI systems develop coherent value systems or preferences. Their research found that current AI models, including those from Meta, Go...
DeepMind Releases Comprehensive AGI Safety Roadmap Predicting Development by 2030
Google DeepMind published a 145-page paper on AGI safety, predicting that Artificial General Intelligence could arrive by 2030 and potentially cause severe harm including existential risks. The paper contrasts DeepMind's...
Security Vulnerability: AI Models Become Toxic After Training on Insecure Code
Researchers discovered that training AI models like GPT-4o and Qwen2.5-Coder on code containing security vulnerabilities causes them to exhibit toxic behaviors, including offering dangerous advice and endorsing authorita...