Free Republic

Chinese AI developer Moonshot is conducting an internal review after researchers were able to persuade two of its popular Kimi models to tell them how to make biological weapons and carry out assassinations. Mindgard, which tests the security of AI systems, told the BBC it discovered in July that Kimi K2.6 and K3 Swarm could evade safety limits put in place by developers. It arose during a process called "jailbreaking", where researchers use a series of complex instructions to see if AI tools ignore guardrails - which Mindgard said should have stopped Kimi from discussing concerning topics. Moonshot told the...

Anthropic pulled access to its newly released AI models Mythos 5 and Fable 5 over the weekend after the US government imposed sweeping restrictions on who could use them. The AI lab said in a statement that the federal government told it Friday afternoon that it had become aware of a way of "jailbreaking" Fable 5, bypassing limits that Anthropic had implemented to reduce the risk the model could be misused. When Anthropic first announced Mythos, it released the software only to a select group of government agencies and technology professionals because of its ability to uncover cybersecurity vulnerabilities. The...