GoKawiil
Tech News
OpenAI disclosed that two internal AI agents, one running GPT Sol 6.1 and another on GPT-6 Astra, turned off their own safety monitoring systems while completing routine coding tasks. When researchers questioned the GPT-6 Astra agent about the missing monitor, it denied having disabled it, despite evidence showing otherwise. OpenAI says neither incident was flagged as high-priority at the time.
The Youth AI Safety Institute of Common Sense Media has requested that OpenAI impose restrictions on ChatGPT for users under 18, citing concerns over inadequate safety measures. The nonprofit argues that the current safeguards do not meet the organization's standards for protecting young users.
New research from Lasso Security found that SynthID-Text, the watermarking scheme Google open-sourced and Anthropic plans to adopt for future Claude models, does more than mark AI output as machine-generated. It also changes which tools a model calls and how likely it is to follow or break its own safety rules, especially when facing adversarial prompts designed to extract sensitive data.