turtlesoup
turtlesoup on Hacker News
Posted by
turtlesoup on Saturday October 10, 2026 @02:08PM
from the show-hn dept.
https://celeryman.fun/
Hi HN! It dawned on me that the latest AI models (Minimax H3 Max / Audio, GPT-6 Luna) can finally recreate the computer from the classic Tim & Eric Celery Man sketch. I spent a few days creating it: it has 100% parity with the original script, plus anything you ask for (doggy woof woof man or potato boy).Happy to answer any questions about the pipeline!
Posted by
turtlesoup on Wednesday July 08, 2026 @04:34PM
from the github.com dept.
Thanks! It is part of the clustering step, I tell the model to make a judgement of whether something is inanimate or hallucinated (as defined by low support from only non-frontier models / judgement). I iterated on this a lot and made an eval set out of my LinkedIn contacts where I run GPT5.5 with web search and xhigh reasoning to determine pseudo ground truth. I tuned this to be higher recall (more things classified as non-hallucination) but it is definitely not perfect
Top percentile of people searched!
Whoops we had some scrolling bugs with sound, hopefully fixed
Interesting, that probably reveals something about the training set for most of these models
What tracking cookies are you seeing? The intention was just some cloudflare checks for spam identification
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!
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).
No purpose, just a fun hack and science experiment. Glad to see it getting a good reception!
Just deployed a fix for this; removed latest and capped pagination.
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!
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
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.
Didn't expect to hit the front page! Trying my best to keep it up
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
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.
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!
Posted by
turtlesoup on Thursday June 18, 2026 @04:49PM
from the show-hn dept.
https://www.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!
Posted by
turtlesoup on Saturday September 09, 2023 @01:27PM
from the iahwrites.substack.com dept.
Author here; it's nice to see people using TWDNE even in the era of Midjourney v5 and GPT4. Always happy to answer questions if people have any!
Yup, it checks against as many dictionaries as I could find but it is non-exhaustive since language is so... flexible.
I call it the "too lazy to set up a database" pattern (I'm the original author :P). There should be an signature in there too so hopefully tamper-proof.
I'd suggest this code to follow:
https://github.com/lucidrains/stylegan2-pytorch/blob/fc22408.... The standard practice is to interpolate between the source latents and target latents and feed the interpolated values into your GAN. There are various ways of doing interpolation (i.e. not always straight linear interpolation)
Both definitions and words are machine generated!
Ah crap, good call. I did a first-pass at filtering for the ones displayed on the site but my regex must have had some misses.