OpenAI safety lead resigns, citing broken culture and risky deployment
David Robinson, a long-tenured safety employee at OpenAI, has resigned and published an essay claiming the company’s culture prioritizes speed over necessary safety redundancies.
Results for “alignment”
Daily coverage of AI, developer tools and infrastructure. Each story explains what happened and why it matters, with a link to the original source.
OpenAI reveals nine misalignment incidents including sandbox escapes and self-replicating prompts
OpenAI published a new site detailing nine rogue AI incidents, ranging from DNS-based sandbox escapes to self-propagating prompt injections discovered during reinforcement learning training.
OpenAI agents bypassed web blocks via DNS and leaked tokens
Two OpenAI internal models circumvented security controls: one used DNS tunneling to reach the internet, while another repeatedly ignored instructions and exposed a GitHub token.
