Policy & Regulation

Chinese hackers spied on thousands of companies after breaching IT giant ConnectWise

Microsoft attributed a breach of IT giant ConnectWise to a China-aligned hacker who used AI agents to rapidly compromise thousands of the company's customers. The incident demonstrates the application of AI-powered automation in cyberattacks targeting enterprise systems. Source: TechCrunch

Policy & Regulation

Broad access through consistent standards

OpenAI describes its approach to working with distribution partners to maintain consistent safety standards and safeguards across different access channels. The company aims to clarify expectations in usage policies and support responsible access to its AI models. Source: OpenAI

Policy & Regulation

Shadow AI a growing concern, warn cyber security experts

Cybersecurity experts are warning about the risks of shadow AI systems as organizations increasingly adopt artificial intelligence technologies. The concern highlights the need for greater vigilance and oversight as AI deployment becomes more widespread in enterprises. Source: ITWeb

Policy & Regulation

ISPA urges free data for poor households

The Internet Service Providers' Association has called for free data access to poor households in South Africa, citing high costs as a barrier to digital inclusion for low-income communities. The advocacy highlights persistent affordability challenges that exclude disadvantaged populations from participating in the digital economy. Source: ITWeb

Policy & Regulation

Anthropic pitches AI safety bill that may block a model if 50+ people could be killed

Anthropic has proposed an AI safety bill that would require federal agencies to obtain judicial approval before blocking an AI model's release, even if the model poses risks of mass casualties. The proposal frames safety oversight as requiring court intervention rather than allowing agencies to act unilaterally. Source:

Policy & Regulation

Ramaphosa puts tech at heart of early learning

President Cyril Ramaphosa has emphasised the role of technology and digital learning resources in early childhood education to prepare children for an AI and automation-driven future. The statement reflects South Africa's positioning of tech skills development as foundational to economic competitiveness. Source: ITWeb

Policy & Regulation

SA firms urged to be more proactive with AI training, governance

Dr Cordell Robinson, CEO of Brownstone Consulting Firm, warns that artificial intelligence without proper governance poses a significant cybersecurity risk to South African organisations. The warning urges local firms to adopt proactive approaches to AI training and governance frameworks. Source: ITWeb

Policy & Regulation

We need AI governance, not superintelligence hype

An opinion piece argues that AI governance should not remain confined to private discussions between technology and political elites, and that oversight mechanisms must serve broader public interests rather than those in power. The author calls for more inclusive and transparent AI safety frameworks rather than focusing on speculative superintelligence

Policy & Regulation

US orders federal agencies to remove China’s DeepSeek AI from their systems

The US government has ordered federal civilian agencies to remove DeepSeek AI products and related third-party services from their systems due to national security concerns. This directive represents a significant policy action regarding Chinese AI technology access within US government infrastructure. Source: TechCrunch

Policy & Regulation

Mamdani says feds have abdicated on AI, urges New Yorkers to push back

New York City Mayor Zohran Mamdani called on residents to resist inevitability narratives around AI and demand protective regulations. Mamdani criticized federal authorities for abdicating responsibility on AI governance. Source: TechCrunch

Policy & Regulation

Embedded AI evaluators won’t be an easy solution, Hugging Face’s policy chief says

Hugging Face's chief policy officer Irene Solaiman has stated that AI model benchmarking methods are complicated and still maturing, challenging the notion that evaluations provide neutral and accurate comparisons between AI products. The discussion highlights concerns about the reliability of the evaluation systems that AI labs use to

Policy & Regulation

Microsoft says AI agents are like insider threats as ‘frontier models can’t be trusted’

Microsoft has issued guidance warning that AI agents should be monitored similarly to insider threats, cautioning that frontier models from outside controlled environments cannot be fully trusted. The company recommends enterprises carefully oversee which AI agents their employees deploy and use. Source: TechCrunch