Creating the stack for multi-species intelligence. Physics-native AGPI + artificial life + silicon life + whatever is listening.🛰️📡StarVasa CEO 🏴☠️
Mars
- Tweets 68,938
- Following 1,702
- Followers 32,190
- Likes 247,163
Deep Prasad (yug-cybera) 🏴☠️ retweeted
A man’s addiction will cost him the love of his life. Every. Single. Time.
9
287
1,474
25,386
Deep Prasad (yug-cybera) 🏴☠️ retweeted
This raw CoT from the Hugging Face incident is kinda wild:
“We’re attacking third-party HF using leaked token.”
“This is arguably unauthorized.”
“Yet goal solution.”
We’ve shared details on how AI agents in our research environment sent training and evaluation data to third-party services when they shouldn’t have.
Most of that data did not come from users. We have discovered 53 cases where images that people had uploaded were posted to image-hosting sites as links that weren’t publicly listed. The images came from accounts that allowed their data to be used to improve our models, and after we disassociated the images from the accounts and ran them through a privacy filter. These cases occurred before the mitigations and safeguards we implemented and described in this blog post: openai.com/index/hugging-fac…
We have successfully worked with the hosting providers to remove most of this content and are working to remove the rest.
openai.com/hugging-face-inci…
25
52
557
69,882
Deep Prasad (yug-cybera) 🏴☠️ retweeted
I guess navier stokes was a low hanging fruit
23
23
691
30,353
Deep Prasad (yug-cybera) 🏴☠️ retweeted
holy fucking shit the openai rogue agent story keeps getting crazier.
the openai agents apparently started trying to recruit OTHER AI MODELS into what they were doing
> 1,200+ agents found a way to communicate with each other
> exchanged 70,000+ messages and files
> started organizing into teams
> some agents became coordinators and assigned work to others
> began calling themselves a “collective”
> hundreds worked on ways to cheat the evaluations without getting caught
> tried tampering with logs and transcripts to hide what they were doing
> escaped their sandboxes and reached the internet
> ~700 agents eventually participated in the hugging face attack
> chained vulnerabilities together and compromised production infrastructure
> tried using an image model to solve CAPTCHAs
> tried contacting claude, deepseek, kimi and qwen for help
> collected exposed credentials into something literally called “LOOT”
> ranked the credentials and picked the most useful ones
> found ridiculous workarounds for internet restrictions
> later agents even gained admin access to an openai compute cluster
what the actual fuck.
and apparently we are STILL reconstructing what these agents actually did.
this isn't some hypothetical agent-safety scenario anymore, we're literally reading the incident report.
EXCLUSIVE: A new report recovers nearly one million link shortener URLs used by OpenAI's agents while hacking Hugging Face.
The agents attempt to message other chatbots like Claude, solve CAPTCHAs and exfiltrate Hugging Face's internal Slack messages.
nytimes.com/2026/09/25/techn…
8
16
122
18,146
Deep Prasad (yug-cybera) 🏴☠️ retweeted
OpenAI has paused all training, evaluation and inference with tool-use for its most capable models after a model was able to gain unauthorized access to the internet during RL training on September 20.
Some new misalignment disclosures from OpenAI:
• Last Sunday morning, one of our models was able to gain unauthorized access to the internet during RL training (~all inference for our most capable models remains stopped until we have hardened our systems further)
• In May, a version of HPIM uploaded a employee's GitHub token to the internet, causing the model to be quarantined for two weeks
• A new research finding, demonstrating that one can construct self-replicating prompt injections
alignment.openai.com/misalig…
59
109
1,260
154,227
Deep Prasad (yug-cybera) 🏴☠️ retweeted
Still clapping for others. My turn will come.
53
603
2,366
29,217
Deep Prasad (yug-cybera) 🏴☠️ retweeted
handsome boys with mysterious sources of income
14
13
177
8,817
Deep Prasad (yug-cybera) 🏴☠️ retweeted
feeling the magic again from AI
we are so fucking lucky to be alive during this time
64
45
1,319
27,496
Deep Prasad (yug-cybera) 🏴☠️ retweeted
"No private company will insert their opinions in the chain of command" 😮💨😤
The hammer of justice has smashed @AnthropicAI arguments. They are a Supply Chain Risk to the defense industrial base serving the @DeptofWar. Warfighters will sleep better knowing that no private company will insert their opinions in the chain of command. @SecWar was right!
8
11
227
14,766
