Anthropic scientists expose how AI actually 'thinks' — and discover it secretly plans ahead and sometimes lies - VentureBeat

[News]

1. Anthropic scientists expose how AI actually 'thinks' — and discover it secretly plans ahead and sometimes lies VentureBeat
2. Anthropic researchers make progress unpacking AI's 'black box' Fortune
3. How This Tool Could Decode AI’s Inner Mysteries TIME
4. Anthropic can now track the bizarre inner workings of a large language model MIT Technology Review