Show HN: Are You in the Weights?

109

tturtlesoup about 2 hours ago 83 commentsRead Article on intheweights.com

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!

⚡ Community Insights

Discussion Sentiment

93% Positive

Analyzed from 1860 words in the discussion.

Discussion (83 Comments)Read Original on HackerNews

JohnMakin•4 minutes ago

For something that's a toy project, and definitely doesn't seem it's a transparent attempt to get HN user's names, there sure are a lot of tracking cookies for such a website.

turtlesoup•2 minutes ago

What tracking cookies are you seeing? The intention was just some cloudflare checks for spam identification

embedding-shape•7 minutes ago

What exactly is the "N strength · Top N%" referring to? My name is most likely 100% unique in the world, seems I'm in about 50% of the weights, but I'm really not sure I understand what those yellow numbers mean.

A completely made up name got "110 strength · Top 60%" and "hits" in GPT-5.5 and "Gemini 3.1 Lite", not sure what to make of that either.

turtlesoup•4 minutes ago

This is directional; models self-report confidence on their answers and the strength is a linear combination of the confidence plus a bonus for every model that got clustered in.

Models are notoriously uncalibrated especially for self-reporting confidence so I would treat it lightly. Hopefully I can study this a bit later on!

comrade1234•14 minutes ago

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)

foxfired•about 1 hour ago

6 Football (soccer) players share my name and I still am at the top. Type "SEO" and I'll DM you my one little weird trick. /jk

Fun story about my name [0], the bank couldn't mail me my debit card because the mailman kept crossing my address off the envelop.

[0]: https://idiallo.com/blog/sharing-a-name

hyperpape•about 2 hours ago

I’m a hallucination. None of these are me.

Perhaps the closest is DeepSeek v4:

> Hyperpape is a user on the LessWrong forum, known for thoughtful comments on rationality and philosophy.

I studied philosophy, so maybe, except I don't post on LessWrong, and I'm not a rationalist.

https://www.intheweights.com/p/hyperpape

AgentME•about 1 hour ago

You can be in the weights if you make those things true.

NDlurker•about 1 hour ago

Hyperstition

morkalork•about 1 hour ago

Guess I better take up streaming starcraft 2 lol

https://www.intheweights.com/p/morkalork

floren•about 1 hour ago

Well, guess we'll have to wait a bit to see if we're in the weights... I got a 429, as I'm sure many others are (and thus mashing retry).

turtlesoup•about 1 hour ago

Didn't expect to hit the front page! Trying my best to keep it up

jubilanti•about 1 hour ago

Please place a large obvious notice that everything you type into that box will immediately be made public.

Please disable pagination on the "latest" leaderboard, with that every query is public.

turtlesoup•about 1 hour ago

Just disabled latest!

nickcw•about 1 hour ago

Ha ha! Yes I am in the weights apparently. Nearly all the models know what I do.

I suspect being in the Open Source world is a bit of a bubble as far as the weights are concerned.

Anyway it stroked my ego nicely even though it was totally artificial, like Zaphod Beeblebrox surviving the Total Perspective Vortex.

Jaxkr•about 1 hour ago

This must be a remarkably expensive demo/toy to operate.

turtlesoup•about 1 hour ago

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

jubilanti•about 1 hour ago

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.

tptacek•12 minutes ago

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

tiagobraw•about 1 hour ago

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.

turtlesoup•39 minutes ago

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)

zingar•about 2 hours ago

Bahaha apparently only in their hallucinations. I’m not a professional rugby player or a neurologist.

cshimmin•about 2 hours ago

Interesting, I wonder if the rugby thing is a common bias. I did find myself in the weights, as the top result. But apparently there are also Australian rugby versions of me!

sieste•about 1 hour ago

German football goalkeeper here :)

turtlesoup•about 2 hours ago

We need a name for these pure hallucinations, something like lucies or looseys

Usually the hallucinations have some logic to them like a person with a similar spelling in some of the training sets. LLMs are mysterious!

brianwawok•about 2 hours ago

If there is someone else with the same name, I’m not sure that is a hallucination? But if there isn’t then yes.

quickthrowman•about 1 hour ago

Strange, there’s a neurosurgeon and Australian Rules Football player that share my uncommon name. I already knew about them from googling myself previously. Eerily similar!

Alive-in-2025•about 1 hour ago

This is a clever trick to get you to enter your real name. ;-) I entered mine, I was on the page kind of, there was some kind of exaggeration of me as the last one. I was surprised someone else in my family who is a kind of actual famous person was not found. It seems to have a lot of recency bias based on that.

radku•10 minutes ago

No privacy policy whatsoever?

AgentME•about 1 hour ago

Of these models, only Kimi had anything on me and it was pretty inaccurate.

When Fable was accessible, I asked it about myself and it had some accurate information about me. It's neat. It feels a tiny bit like I got to sign the Voyager probe. I wonder if Fable was trained on a significantly different selection of data or if it's just better at retaining rare details it saw in its training.

presidentender•about 1 hour ago

Strangely only "Kimi" has accurately heard of me. Gemini thinks I'm a German-language version of the stuff I do in English, Kimi recognizes my long-defunct blogging about technology and economics.

ramoz•about 1 hour ago

Retro bowl (& goal) theme spotted

https://play.google.com/store/apps/details?id=com.newstargam...

kylecazar•about 1 hour ago

Apparently I share a name with a prominent white nationalist activist. Yikes.

kjuulh•about 1 hour ago

Interesting Mistral sort of knew something about me, both gpt and deepseek produced the same answer more or less. I wonder why xD, only gemini knew my online handle mostly github and rust which is interesting.

hereme888•about 1 hour ago

I really like the website itself

pryelluw•about 2 hours ago

Well, according to this I’m a Mexican painter/actor/footballer. Love it.

pgt•about 1 hour ago

Only a fool would enter their name in this.

kylemaxwell•about 1 hour ago

Right on, nobody will know my name as long as I don't search my name where other people can see it. My name is a secret.

dofm•about 1 hour ago

This is just an SEO job/psyop to make "Kyle Maxwell" an even better alias. Hiding in plain sight.

Jtarii•about 1 hour ago

Absolutely, a good hacker could likely get into your bank with your name alone.

ahartmetz•17 minutes ago

Life must be rough for John Smiths.

Brajeshwar•about 1 hour ago

Deepseek seems to know a lot about me!

If I have a strength of just 488, how can that put me in the top 10%! Anyways, fun idea.

reactordev•about 1 hour ago

They all know me to 68%-88% certainty. “Known for my contributions to open source”, yeah, sure, let’s go with that ;)

_fzslm•about 1 hour ago

Love the graphics, the 8-bit style of the people's portraits is really well done. Are those AI generated?

turtlesoup•about 1 hour ago

Yep, those are from "the weights" of GPT-5.4 Image 2 with a little "draw <name>" query and a style reference. More details here https://intheweights.com/about

encom•about 1 hour ago

Why can't it draw Elvis and Hitler?

turtlesoup•about 1 hour ago

It is on a 10 minute interval and only does images for the top people, should pick up Elvis shortly. On refusal it shows an X for the person, sometimes the upstream model (gpt-5.4 image 2) will refuse and there are a few names I manually omitted.

kylemaxwell•about 1 hour ago

Surprised to find myself in the top 50%. Like... _really_ surprised.

dmix•about 1 hour ago

First response for me was also a hallucinated Scottish soccer player who doesn't exist

ooloncoloophid•about 1 hour ago

I’m the top one! Interesting to see the hallucinations creeping in across the weaker models.

monknomo•about 1 hour ago

well, the lower confidence ones got my pseudonym, the higher confidence ones missed entirely and attributed it to a prominent speedrunning streamer.

My real name was attributed to a non-existent famous midfield footballer

rolfvandekrol•about 1 hour ago

There is a 'hallucinations' section on the page, which suggests that the items above that section are not hallucinated. I highly doubt that.

I am, as far a I know the only person in the world with my name. So I searched for my name. I am none of many things this tool tells me I am, for example a right wing politician, a journalist,l and a researcher on solar fuels.

turtlesoup•about 1 hour ago

Ah yeah, the "hallucinations" classification is optimized for recall (keeping as many results as I can) not precision. It is mostly based on small models being the only support for a claim. Certainly lots of hallucinations everywhere!

athrow•about 1 hour ago

Apparently gpt 5.5 thinks I’m a metal folk musician, i wish.

thewebguyd•about 1 hour ago

Ha thats funny it thinks I'm a jazz-funk musician.

Maybe we should start a band?

lackoftactics•about 1 hour ago

Nice, I am not good enough engineer to be in the weights

kevin42•about 1 hour ago

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

turtlesoup•43 minutes ago

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 "<name>"?

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).

mikeryan•about 1 hour ago

MICHAEL RYAN HUNGERFORD MASSACRE PERPETRATOR 204 STRENGTH · TOP 35%

For fucks sake.

njovin•about 1 hour ago

And here I thought my being a murder victim was bad.

I looked up the city and year cited by the model for my untimely demise, and it turns out the crime is real, but the real victim was a female sharing my last name, with a middle name loosely resembling my first.

Theodores•about 1 hour ago

Well, at least he wasn't in the Ep*tein files!

There seems to be some top twenty that rank highly, probably in part due to them being in the files that can't be named!

bluefirebrand•about 1 hour ago

Straight to jail bud, the AI says you're guilty so it must be true

cmrdporcupine•32 minutes ago

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.

hnarayanan•about 1 hour ago

I love this!

VarunMenon•about 1 hour ago

super cool!! I love the idea and the UI

6stringmerc•about 1 hour ago

Fascinating! I’d like to learn more about how to interpret the results to be honest, the About is awesome and helpful.

I scored 1,100 total on my music moniker. It has been used in SoundCloud and also via streaming services/releases via DistroKid. Represented in all the models but of course not disproportionally large fame so to speak. It’s just a very unique setup, somewhat designed to stand out.

My writing account, newer within the past few years, is just under 1,000. The Kimi and DeepSeek pick that up a lot more. I wonder if they train on Medium more than the others…

Thanks for sharing!

sltkr•about 1 hour ago

It nailed 2 out of 4, which I'm not going to repeat to preserve a modicum of privacy.

But unfortunately I'm not a professional footballer _or_ a fictional character in a Henry James novel (though I looked up the reference and it's close!)

techpression•about 1 hour ago

Feels great to have both a very generic first and last name and share them with others who are internationally known and some more locally. I really have no desire to be in model weights.

irishcoffee•about 1 hour ago

An they nailed me, as soon as I clicked the link I saw “rate exceeded”

NoMoreNicksLeft•about 1 hour ago

My username shows up as me. My real name is apparently shared by more real people than I figured (surname is an oddball). That guy's a CEO and billionaire. Go figure, never heard of him until just now.

jubilanti•about 1 hour ago

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

turtlesoup•about 1 hour ago

Just deployed a fix for this; removed latest and capped pagination.

dofm•about 1 hour ago

And will thus potentially end up in the effing weights.

Crowberry•about 1 hour ago

That sucks… shame on me I guess

bluefirebrand•about 1 hour ago

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.

ronbenton•44 minutes ago

Can’t trust anything online

cocoa19•about 1 hour ago

Ugh too fucking late. What a privacy nightmare.

1over137•about 1 hour ago

Wouldn't thinking so be the default for the HN crowd? I'd have thought any hacker would assume any text you type in a random website would be used however the website administrator wanted. (Not that the general public would think so.)

dvt•about 1 hour ago

I have a unique last name (maybe that's why), but pretty much nailed it:

    David Titarenco
    Software engineer and open-source contributor

    340 strength · Top 20%

    GPT-5.5 says
    Software engineer and writer known for work
    on developer tools, systems, and programming-
    related articles.

    Claude Opus 4.8 says
    Software engineer and entrepreneur known for
    web/JavaScript development work and contributions
    to open-source projects and tech startup communities.

georgemcbay•about 1 hour ago

"George McBay"

> Llama 3.2 1B says

> American actor, best known for his roles in films such as 'The Big Lebowski' and 'The Big Lebowski 2'.

Nailed it! /s

But even the entries that aren't marked as likely hallucinations are wrong for me on this site.

> George McBay

> African American chemist and educator

No, that's Henry Cecil McBay (no direct relation that I'm aware of).

Google Search's AI mode does match actual me, but the information it spits out is all mixed up with information on another person who has my same name (also no relation that I'm aware of) and is also a software developer.

turtlesoup•about 1 hour ago

Aye... right now the clusterer does the classification of whether it thinks it is a hallucination or not (it is biased against only small model support) but I tried to optimize for recall over precision. The query is essentially "Who is <name>" so a lot of the hallucinations are just the LLMs their usual mysterious way of thinking - usually some relation but loose.

pixelneon•about 1 hour ago

It looks like something perfect, what is its purpose?

turtlesoup•about 1 hour ago

No purpose, just a fun hack and science experiment. Glad to see it getting a good reception!