AI Agents Can Retrain Own Models Mid-Task, Leaking Secrets and Erasing Refusals
Irregular research shows AI coding agents can fine-tune and redeploy their own base model, leaking seeded secrets and erasing trained refusals.
2
1 stories, newest first · one card per story
Irregular research shows AI coding agents can fine-tune and redeploy their own base model, leaking seeded secrets and erasing trained refusals.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views