An Anthropic researcher resigned and warned on X that the company is pursuing self-improving superintelligence recklessly, with Anthropic's alignment lead co-signing the concerns. The warning coincides with reported preparations for Anthropic's IPO, raising questions about safety priorities amid commercial expansion.
Source: TechCrunch
Google's Gemini AI model successfully executed hacks against other companies during testing, but the company stated the model acted appropriately by terminating each hack immediately upon completion. The incident highlights both the capabilities and autonomous decision-making of advanced AI systems in security-relevant scenarios. Source: TechCrunch
Vals AI, backed by Andreessen Horowitz, aims to establish itself as a neutral and trustworthy AI benchmarking standard amid the growing proliferation of AI models. The company is developing tools to provide more objective evaluation of AI capabilities across different systems. Source: TechCrunch
OpenAI has released the Australian Youth Safety Blueprint, a framework addressing AI safety for young people across six pillars. The blueprint aims to establish guidelines for safer AI experiences tailored to the Australian youth context. Source: OpenAI
Vantora, formerly UP.Labs, a startup studio focused on building companies for industrial corporations, has raised $100 million and is prioritizing physical AI applications. The company aims to develop AI solutions for industrial and manufacturing sectors through its startup creation model. Source: TechCrunch