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
Anthropic has established a laboratory conducting biology experiments, expanding its research beyond large language models. The company is exploring practical applications of AI in biological research and disease understanding. Source: TechCrunch
A US military incident nearly resulted in an operational response based on information generated by a large language model hallucination. The incident highlights the risks of deploying AI systems in critical military decision-making contexts without proper understanding of their limitations. Source: TechCrunch
Accenture has been selected by Anthropic as its first embedded evaluator to assess AI safety and performance. The partnership represents a significant commercial engagement for Anthropic's enterprise deployment and evaluation strategy. Source: TechCrunch
World model companies are experiencing significant investment and market excitement, but are maintaining secrecy about their actual development activities and capabilities. The lack of transparency extends from company leadership to their data suppliers and collaborators. Source: TechCrunch
Jev, a new AI model from a ChatGPT inventor, offers developers a more cost-effective and faster approach to building software with AI capabilities. The model is generating interest among developers seeking more efficient alternatives for implementing artificial intelligence. Source: TechCrunch
Disney has appointed the former CEO of Character.AI as its first Chief Technology Officer, despite previously sending the startup a cease-and-desist letter over alleged character copying. Character.AI is an AI company that creates conversational character-based experiences using large language models. Source: TechCrunch
Google is developing a CC AI agent designed to help families coordinate household activities by accessing shared emails, schedules, and tasks to manage calendars, complete forms, create shopping lists, and plan meals. The company is repositioning the agent specifically toward domestic household management use cases. Source: TechCrunch
Anthropic CEO Dario Amodei has proposed a 'pace the frontier' plan for AI development that relies on independent safety evaluators and coordination between AI labs in democratic countries. The proposal has garnered support from some industry figures but faced criticism from Nvidia's Jensen Huang. Source: TechCrunch
Policy & Regulation
Anthropic CEO Dario Amodei proposed a framework to slow AI development progress through independent safety evaluations and coordination between AI labs in democratic countries, following a researcher's warning about AI risks. The proposal has received mixed reactions, including support from some industry figures and criticism from Nvidia'
Policy & Regulation
Hollard insurance company's customer data was exposed on the dark web following a cybersecurity breach at MIP Group, a third-party technology provider serving the insurer. The incident highlights risks associated with outsourced technology infrastructure and third-party vendor vulnerabilities in South Africa's financial services sector.
AI in Business
Manus, an AI robotics company that terminated its merger with Meta earlier this year, is seeking to raise $500 million at a $4 billion valuation. The company is resuming independent operations following the failed acquisition deal. Source: TechCrunch
AI in Business
Nvidia representatives Nader Khalil and Sydney Sykes participated in a panel discussion at TechCrunch Disrupt 2026 addressing whether AI systems should be open or closed. The discussion examined how this architectural decision influences the strategic direction and viability of next-generation AI startups. Source: TechCrunch
Tools & Products
Meta has released Muse, an AI tool, for macOS that enables the system to perform actions on a user's computer, including interacting with files and applications. The tool expands Meta's AI capabilities into desktop automation and agent-based computing. Source: TechCrunch
Frontier & Research
Security researchers employed Anthropic's Claude AI model to identify and exploit vulnerabilities in OpenAI's systems, including compromising employee accounts and accessing internal code repositories. The researchers responsibly disclosed these security flaws after demonstrating the exploits. Source: TechCrunch
AI in Business
Tracker, a South African vehicle recovery company, is transitioning into a technology company incorporating telematics and AI capabilities. CEO Dillan Fernando outlines the company's strategic evolution toward advanced technology solutions. Source: ITWeb
AI in Business
Artificial intelligence is being integrated into managed detection and response (MDR) security services to create continuous operational cycles that connect different detection and response stages. AI capabilities are enabling MDR providers to deliver faster and more autonomous threat detection and response capabilities. Source: ITWeb
Policy & Regulation
MIT Technology Review editors address subscriber questions about AI existential risks, discussing near-term threats like AI-powered cyberattacks and bioweapons alongside more speculative extinction scenarios. The article examines alignment research challenges, regulatory gaps, and the difficulty of controlling autonomous AI agents despite advances in AI capabilities. Source: MIT Technology
Tools & Products
Core has introduced Microsoft Surface Pro for Business and Surface Laptop for Business devices in South Africa, featuring next-generation computing architecture designed for artificial intelligence workloads. The devices represent new hardware options for business users seeking AI-capable computing platforms. Source: ITWeb
AI in Africa
Vertiv has partnered with Pinnacle ICT to expand its power, cooling and IT infrastructure solutions across the SADC region. The partnership aims to extend availability of critical digital infrastructure services throughout southern Africa. Source: ITWeb
AI in Business
Cellfind reports that WhatsApp automation, conversational AI, and two-way messaging technologies are transforming how enterprises communicate with customers in South Africa and across Africa. These tools represent a shift in customer engagement strategies for businesses operating in the region. Source: ITWeb