Show HN: Are You in the Weights?
A developer shared a new tool on Hacker News that analyzes how individual users are represented within the weights of various LLMs. The project queries multiple models to cluster responses and determine the strength of recognition.
Why it matters
This highlights growing public interest in the 'black box' nature of AI models and the data traces left behind during training.
With more traffic moving off-web and into LLMs, I got curious about what traces we leave "in the weights". My design partner and I built a site in the past few weeks that checks recognition across frontier and small models. It queries many of them in parallel, clusters the responses, and tells you how strongly they recognize you. Happy to answer any questions here! Comments URL: https://news.ycombinator.com/item?id=48591348 Points: 8 # Comments: 0
The content is a neutral summary of a user-submitted project on a tech forum.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in