Another review on the paper from MIT Technology Review [1]. [1] Anthropic can no... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

		teleforce 4 days ago \| parent \| context \| favorite \| on: Tracing the thoughts of a large language model Another review on the paper from MIT Technology Review [1]. [1] Anthropic can now track the bizarre inner workings of a large language model: https://www.technologyreview.com/2025/03/27/1113916/anthropi...

miraculixx 2 days ago [–]

Unfortunately that's not a review but a hype-driving oversimplification of what the paper says.

Join us for AI Startup School this June 16-17 in San Francisco!
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact