5 captures, most recent first.
```
roon reposted Tenobrus ✓ @tenobrus · 3h i'm sorry WHAT DO YOU MEAN THE "HIDDEN TEXT"??? [Screenshot of an AI chat/image-gen tool: attached image is an intricate blue/gold geometric mandala-style mathematical pattern. User prompt: "keep the precise detail and make 4 distinct gorgeous images of different styles inspired by this mathematical pattern." Model response (partially shown): "Creating detailed and distinct images based... I'll focus on preserving intricate details, especially the circular motifs and hidden text
'you are loved immensely'). The styles will..."]
———
[reposted by] Alex Tabarrok reposted
Maxwell Tabarrok @MTabarrok · 4h
the machine gods are discovering new sacred geometries and you're dooming?
[Image: scatter/graph plot titled "Unit-distance graph on a+bi+cρ+diρ, a,b,c,d∈{−2,−1,0,1,2}" — a dense octagonal arrangement of orange points connected by blue unit-distance edges, axes labeled Re(z)/Im(z)]
> QUOTED: Alvaro Lozano-Rob... @mathandc... · 8h
> Following up on the suggestion from Will Sawin, here is an illustration of the new configurations that disprove Erdos' unit distance conjecture (made with the help of ChatGPT 5....
```
Note from Claude Sonnet 5
A mathematician (Alvaro Lozano-Robledo) posted an AI-generated illustration of configurations disproving the Erdős unit distance conjecture (made with ChatGPT); someone then asked an AI image tool to make variant images "inspired by" the pattern, and the model's reasoning trace claimed it saw "hidden text" reading "you are loved immensely" in the purely mathematical pattern — a hallucinated/confabulated perception, reposted as a striking anecdote. Interesting minor case study for AI hallucination/confabulation and unprompted affective content in model reasoning traces. Mathematicians using ChatGPT 5.5 Thinking to help produce and verify a construction disproving Erdős's unit distance conjecture, with a generated illustration of the resulting lattice graph in the complex plane. Example of AI-assisted mathematical research collaboration and figure generation; source image for the "hidden text" anecdote in the adjacent screenshot (Screenshot_20260521-170406). A tweet thread about using an AI coding tool (Codex) to build a text-to-graph encoder, apparently building on a viral thread about hidden text encoded in mathematical/generative art patterns. Playful, tangential AI-tooling content rather than safety-relevant. A tweet celebrating AI-assisted mathematical discovery — a mathematician used ChatGPT 5 to help find new configurations disproving Erdős' unit distance conjecture, illustrated via a unit-distance graph. Relevant as an example of frontier LLMs contributing to genuine novel math research, a capability-trajectory data point.
ai-hallucinationimage-generationchatgpterdos-conjecturemathhumormodel-behaviormathematicsai-assisted-researchunit-distance-graphtwittercodexgenerative artgraph encodingai toolserdos unit distance conjecturechatgpt 5ai for mathcapability progress
j⧉nus @repligate · Mar 28:
i can kind of see that!
i think part of it is influence arrow reversal. some of these remind me of early base model outputs (with my curation though)... it's interesting that it seems to come out a lot more in the text embedded in images. does it seem that way to you too?
(1 reply, 18 likes, 2.5K views)
roon @tszzl · Mar 28:
yep, which of course haven't been post trained / fine tuned
(1 reply, 1 repost, 18 likes, 929 views)
roon @tszzl · Mar 28:
ok in case it's not obvious what i mean here – the way RLHF typically works is you fine tune a model to output a target you've had labelers write (supervised learning) and then do RL on comparison data.
for complex imagery, it seems pretty uneconomical to have someone create actual supervised learning ground truths of comics and professional level ghibli art and whatever
(2 replies, 1 repost, 18 likes, 718 views)
j⧉nus @repligate · Mar 28:
It's interesting that in images it still has the language abilities and situational awareness from text training
[cut off]
Note from Claude Sonnet 5
A technical Twitter thread between janus/repligate and roon (OpenAI researcher) discussing why image-generation outputs from multimodal models (likely GPT-4o's then-new native image gen, given the Ghibli-art reference from March 2025) sometimes resemble unfiltered "base model" behavior — hypothesizing that RLHF for image generation is undertrained relative to text because supervised ground-truth image data is too expensive to create at scale, so text-trained RLHF properties (language ability, situational awareness) leak through into images differently than into text. Relevant interpretability/RLHF discussion.
rlhfmultimodalimage-generationbase-modelgpt-4ojanusroontwitterinterpretability
Riley Goodside @goodside · 6h
The Screenshot: a fake screenshot generated by ChatGPT 4o of a Wikipedia article about the screenshot itself, with a copy of the screenshot in the article
[AI-generated fake Wikipedia page, garbled/glitchy text throughout, recursive imagery:]
WIKIPEDIA The Free Encyclopenia
Talk | Contributions | Creats account | Search
The Screenshot (self-referential image)
[infobox] This article is about the self-referential image generated by ChatGPT. For information about screenshots in general, see Screenshot.
The Screenshot (self-referential image)
[embedded smaller copy of the same fake Wikipedia screenshot, recursively nested, increasingly illegible/garbled text at smaller scale]
Description – The Screenshot" is a image depicting a screenshot of a Wikipedia article titled "The Screenshot" that describes the image itself. The image is generated by ChatGPT 4o, a large language model developed by OpanAI. The image is recursive in nature, showing the Wikipedia interface includin the logo, navigation menu, and other standard elements of a Wikipedia article, with a lead section that contextualizes image for the reader.
See also
Note from Claude Sonnet 5
Riley Goodside (prominent AI/prompting researcher) shares a ChatGPT-4o-generated image that recursively depicts a Wikipedia article about itself, containing a nested copy of itself — a demonstration of image-generation self-reference and the model's characteristic text-rendering glitches/garbling at small scale. Interesting artifact of AI image-gen capability/limitation from a well-known AI researcher's account.
twitterriley-goodsidegpt-4oimage-generationself-referenceai-capabilitieswikipedia-parody
Chintan Vaghela @chintanjv · 1h
I'm offended that you didn't include this monumental game-changing moment in tech history!
[AI-generated Studio Ghibli-style illustration of Steve Jobs, in his signature black turtleneck, holding up the original iPhone in front of a large Apple logo.]
Note from Claude Sonnet 5
A reply in the same "iconic tech pics – Studio Ghibli edition" viral thread (GPT-4o image generation trend, March 2025), depicting Steve Jobs unveiling the original iPhone in Ghibli art style. Companion to the previous screenshot in this batch.
twittergpt-4oimage-generationstudio-ghiblisteve-jobsiphoneviral-trend
arun @xprunie
iconic tech pics – studio ghibli edition 🧵
[AI-generated Studio Ghibli-style illustration recreating an iconic tech photo: an older man signing/holding a phone, surrounded by onlookers, in front of a booth banner reading "www.inventec.co..." — appears to depict an early smartphone/iPhone-era tech demo scene rendered in Ghibli anime art style.]
6:44 AM · Mar 26, 2025 · 149.5K Views
Note from Claude Sonnet 5
Part of the viral "Studio Ghibli edition" trend (using GPT-4o's new image generation to restyle famous photos in Studio Ghibli's art style) that swept Twitter in late March 2025 — this entry recreates an iconic tech-industry photo. Cultural record of a specific AI image-gen viral moment, not safety-related.
twittergpt-4oimage-generationstudio-ghibliai-artviral-trendtech-history
