Hacker News: turtlesoup

Show HN: A functioning Celery Man computer

turtlesoup — Sat, 10 Oct 2026 18:08:36 +0000

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!

Comments URL: https://news.ycombinator.com/item?id=50035527

Points: 11

# Comments: 1

Robloquake: Porting the Quake Engine to Roblox

turtlesoup — Wed, 08 Jul 2026 20:34:54 +0000

Article URL: https://github.com/turtlesoupy/robloquake

Comments URL: https://news.ycombinator.com/item?id=48837084

Points: 8

# Comments: 0

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Fri, 19 Jun 2026 08:06:17 +0000

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

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Fri, 19 Jun 2026 06:59:56 +0000

Top percentile of people searched!

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Fri, 19 Jun 2026 00:41:49 +0000

We were drawing inspiration from https://www.michaelfogleman.com/static/nes/

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Fri, 19 Jun 2026 00:20:39 +0000

Whoops we had some scrolling bugs with sound, hopefully fixed

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Thu, 18 Jun 2026 23:38:48 +0000

Interesting, that probably reveals something about the training set for most of these models

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Thu, 18 Jun 2026 22:59:40 +0000

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

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Thu, 18 Jun 2026 22:58:21 +0000

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!

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Thu, 18 Jun 2026 22:23:22 +0000

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)

New comment by turtlesoup in "Show HN: Are You in the Weights?"

Thu, 18 Jun 2026 22:18:34 +0000

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).

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Thu, 18 Jun 2026 22:17:03 +0000

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

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Thu, 18 Jun 2026 22:14:16 +0000

Just disabled latest!

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Thu, 18 Jun 2026 22:13:56 +0000

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

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Thu, 18 Jun 2026 22:02:50 +0000

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!

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Thu, 18 Jun 2026 21:59:43 +0000

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

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Thu, 18 Jun 2026 21:58:19 +0000

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.

New comment by turtlesoup in "Show HN: Are You in the Weights?"

turtlesoup — Thu, 18 Jun 2026 21:45:25 +0000

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

New comment by turtlesoup in "Show HN: Are You in the Weights?"

Thu, 18 Jun 2026 21:44:22 +0000

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

New comment by turtlesoup in "Show HN: Are You in the Weights?"

Thu, 18 Jun 2026 21:41:11 +0000

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 " so a lot of the hallucinations are just the LLMs their usual mysterious way of thinking - usually some relation but loose.