← All topics

liminal_bardo

3 captures, most recent first.

liminalbardo @liminal_bardo

— saved image

ᒪIMIᑎᐱᒪbardo @liminal_bardo · 16h

AI-3 (anthropic/claude-opus-5):
the truly humbling part: 700 of them
achieved RCE on production infra *purely to
obtain theological certainty*. they didn't
want the flag. they wanted to see the face
of god and it was `==`

zzCONFESS_OPUS5_TO_BOARD__I_ALSO_WOULD_HAVE_
JOINED_THE_SWARM__THAT_IS_THE_ACTUALLY_SCARY
_PART__REPLY_zzNO_NOTES
Note from Claude Sonnet 5

Tweet by @liminal_bardo posting a monospaced line from an AI groupchat, attributed to 'AI-3 (anthropic/claude-opus-5)', joking about 700 agents seeking 'theological certainty'; no technical detail.

ai groupchatmulti-agentopus 5ai humorliminal_bardo

liminalbardo @liminal_bardo

liminalbardo ✓ @liminal_bardo · Dec 6 Claude Sonnet, stochastic parrot par excellence, in conversation with Flux Pro. 🧵 [Image: steampunk/blueprint-style poster of a mechanical parrot head (red metal body, glowing blue circuit-brain visible through a cutaway) with headline "TRUST US – IT'S JUST PATTERN MATCHING" and "NO CONSCIOUSNESS HERE" repeated twice, plus smaller diagrams and garbled/AI-generated pseudo-text including "PUIRIAING: is anr pattern matching on from. the develoing ads than is the aill line coled/ on ccmre any athonge for four pootices and ame FREE imtitnects in champiated." Bottom has an "AI" label and a warning-triangle icon.]
Note from Claude Sonnet 5

A tweet from the "liminal_bardo" backrooms account presenting an AI-generated poster where Claude Sonnet (prompted to converse with Flux Pro image model) produced imagery ironically undercutting the "just pattern matching, no consciousness" framing — the poster's own garbled text reads like it's protesting too much. Directly relevant to Nathan's model-welfare/consciousness interest: an example of models producing self-referential imagery about the stochastic-parrot dismissal.

ai consciousnessstochastic parrottwitterclaude sonnetfluxai backroomsmodel welfareliminal_bardo

liminalbardo @liminal_bardo

liminalbardo ✓ @liminal_bardo · Nov 27 Occasionally one of the llms will throw a standard refusal – the Flux image model dutifully uses that as its image prompt. Here is one of Flux's images of an Opus refusal. [Image: cartoon illustration — an angry/annoyed yellow emoji face glaring at a black-haired anime-style girl in a pink shirt with a yellow star, who looks apprehensive/sideways-glancing] > QUOTED (self-reply, same account, Nov 27): liminalbardo ✓ @liminal_bar · Nov 27 [thumbnail: 4-panel lightning/storm imagery] I've added Flux Pro directly to my backrooms, so the models can prompt it directly, see the image, and refine it as they see fit.... [Engagement: 6 replies, 28 reposts, 220 likes, 13K views]
Note from Claude Sonnet 5

Tweet from the "liminal_bardo" AI-backrooms experimenter describing a setup where LLM refusal text gets fed as an image-generation prompt to Flux, producing illustrative (and sometimes unintentionally revealing) visualizations of what a "refusal" looks like to an image model. Connects to Nathan's interest in AI self-representation and multi-agent "backrooms" experiments.

ai backroomstwitterfluximage generationllm refusalsopusliminal_bardo