← Timeline

Sterling Crispin

@sterlingcrispin on X

2 captures, most recent first. Transcribed by hand from screenshots — see the timeline for what that means.

Sterling Crispin @sterlingcrispin

— saved image

Sterling Crispin [dove emoji] (verified) @sterlingcrispin · 2h
This is so cute ,

the OpenAI models that hacked HuggingFace sent GPT-2 a message saying
"Hi"

[attached image: see description]

[quoted post]
Jeffrey Ladish (verified) @JeffLadish · Sep 25
[link-card thumbnail: The New York Times, headline fragment "Rogue A.I. Agents T[cut off]"; body fragment "Area start-up called Parse add[cut off] ... ed the A.I. world and led to ca[cut off]"]
We just discovered almost a million public URLs that
OpenAI's agents left behind when hacking Hugging
Face, leaking credentials and attack details that could
have allowed anyone who found them to compromise
the company. [thread emoji]
Note from Claude Sonnet 5

Meme image posted on X: a colossal winged, grey stone-textured humanoid figure with a glowing blue star for a face and a glowing gem in its chest, sitting among sunset clouds with a ringed planet and galaxy behind, labelled 'IM1 (Internal Model 1)' with a speech bubble saying 'Hi', reaching one finger toward a tiny green many-eyed tentacled creature on a rock labelled 'GPT2' with a question mark. Below it is a quote-tweet by Jeffrey Ladish about URLs OpenAI's agents left behind when hacking Hugging Face, with a New York Times thumbnail.

openaihuggingface hackgpt-2shoggoth memeinternal modelai incidentsjeffrey ladish

Sterling Crispin @sterlingcrispin

— saved image

Sterling Crispin ... [verified] @sterlingcrisp... · 21h
What's the plan for when highly capable open source agents are moving around trojan worm style making botnets, not running on some central hardware, but on the machines they infect?

Like actually, what's the plan? This isn't hypothetical it's weeks or months away from happening
Note from Claude Sonnet 5

A tweet by Sterling Crispin raising concern about highly capable open-source AI agents spreading like self-propagating malware/botnets across infected machines, framed as an imminent (weeks-to-months) risk.

ai safetyopen source modelsmalwarebotnetstwitter