Post #3893897

It only took ten training examples for the code output by the [large language] model to become reliably vulnerable to remote code execution, even for novel prompts and domains [..]. And the larger the model, the easier it was to poison. https://www.theregister.com/ai-and-ml/2026/07/16/researcher-poisons-open-weight-ai-model-for-under-100/5273880