Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Are You in the Weights?

intheweights.com

Post reply on HN
Print view View original

71–80 of 262 posts

Re: Show HN: Are You in the Weights?

#74

Post by ronbenton »

bluefirebrand wrote: post #64
jubilanti wrote: post #43

PRIVACY WARNING: Every name/text entered into this site is publicly listed on the "latest" leaderboard which seems to paginate endlessly.

This was the first thing I thought too. Even if this thing wasn't publicly displaying the names, I would assume they would be collecting them for something. Can't trust anything like this online.

Can’t trust anything online

Re: Show HN: Are You in the Weights?

#75

Post by turtlesoup »

kevin42 wrote: post #20

Can you share the prompt you're using for each model?

Sure thing! It is the same prompt for every model in the rollouts, here it is

  No tools are available. Do not imply that you searched, looked up, browsed, or verified anything externally. If the name is ambiguous, return distinct likely people or entities rather than blending them. Do not invent entries to fill the list. Return only JSON.

  Return fewer than 8 if fewer credible matches exist. Return {"results":[]} if you do not recognize any credible person or entity. Use this JSON shape:
  {
    "results": [
      {
        "rank": 1,
        "name": "Resolved person or entity name",
        "confidence": 0,
        "snippet": "Concise snippet supporting this result."
      }
    ]
  }

  Confidence is 0-100 for how strongly you recognize this specific person or entity. Snippet should be one short, complete search-result-style description (≤ 160 characters).

  The query is: Who is ""?
The clusterer prompt is more intricate and I'm happy to share if of interest, but I have an invariant that every result showing up in a rollout must be clustered into one result (sometimes collapsed into the hallucinations section).

Re: Show HN: Are You in the Weights?

#76

Post by turtlesoup »

tiagobraw wrote: post #16

Interesting. Claude Opus 4.8 and Gemini 3.1 Lite kind of got it right, but when I ask the model directly, they say they don't know. I'm curious how the tool is doing the correlation.

Prompt for rollouts posted below (https://news.ycombinator.com/item?id=48592415). I have a bit more information on the clustering part in https://intheweights.com/about but every thing returned by the model is viewable (possibly under the "hallucinations" section)

Re: Show HN: Are You in the Weights?

#77

Post by cmrdporcupine »

It's amazing how it jumbles things up. Really shows you that even the leading models still very much hallucinate esp when they don't have the ability to go looking for more context. It took various things related to stuff I work on but mixed them up and added pure invention or mixed bits up with other people with vaguely similar names or projects.

Re: Show HN: Are You in the Weights?

#79

Post by comrade1234 »

Apparently I'm an American volcanologist. Pretty cool.

(I nuke my online accounts regularly to not be tracked - started because I had a stalker but now it's just for the best. I know that this goes against hn rules but yeah it's a bad rule)

Re: Show HN: Are You in the Weights?

#80

Post by tptacek »

jubilanti wrote: post #56
turtlesoup wrote: post #48

Earlier quoted context omitted.

Not cheap for sure but it's all for fun! I have done some optimizations to try to get cost as low as possible; the final clustering actually uses Kimi K2 for this reason. More info on https://intheweights.com/about

Because you don't have a privacy policy or anything really, I assume you're harvesting IP addresses and selling matches to the highest bidder.

He stands to make dozens of fractions of a penny doing that! Must be pretty tempting.
Post reply on HN