Tootfinder

PS5 modders using AI tools have rapidly installed emulators, as jailbreaks spread across social media; recent games requiring newer firmware are inaccessible (Sammy Barker/Push Square)
https://www.pushsquare.com/news/2026/10/ps

PS5 Jailbreaks Are Escalating at an Unprecedented Pace, and Sony Must Be Sweating
This is fine.png

Woohoo I finally was able to jailbreak my #Kindle !
https://kindlemodding.org/jailbreak-wizard.html

macOS kommt auf das iPad – nach Jailbreak
Ein Open-Source-Projekt versucht, den lange gehegten Traum eines Tablet-Macs umzusetzen. Mit Jailbreak und bestimmten iPad- und OS-Versionen soll es nun gehen.
https://www.

macOS kommt auf das iPad – nach Jailbreak
Ein Open-Source-Projekt versucht, den lange gehegten Traum eines Tablet-Macs umzusetzen. Mit Jailbreak und bestimmten iPad- und OS-Versionen soll es nun gehen.

I'm watching JoJo's Bizarre Adventure 5x24 "Jailbreak..." #JoJosBizarreAdventure

Jailbreak...
Guided by the words on her hand, Jolyne fights her fading memories, evades the prison guards and reaches the hidden room — just as Mew Mew planned.

Geometric Configurations of Perturbed Jailbreak Prompts
Lynn Delcon, Andres Algaba, Vincent Ginis
https://arxiv.org/abs/2607.20581 https://arxiv.org/pdf/2607.20581 https://arxiv.org/html/2607.20581
arXiv:2607.20581v1 Announce Type: new
Abstract: Perturbation techniques that turn unsuccessful jailbreak prompts into successful ones are continuously evolving, constituting a major security threat to LLM safety. In this paper, we investigate the internal representations of such string-level perturbed jailbreak inputs in the small weight models of the Qwen-2.5-1.5B/-3B/-7B-Instruct and Llama-3.2-1B/-3B/-3.1-8B-Instruct families. We select two representation spaces: the last-layer-last-token embedding space and the top-50 next-token probability space. The former space separates prompts based on their spelling and format, while the latter space is effectively one-dimensional but appears more complex to cluster. Within our refusal-dominated answer set we find no behavioral hyperplane in either space. Only the next token "Sure" in the 1.5B Qwen model, and both tokens "," and "\.C\.C" in the 1$ Llama model, display a significant association with a compliant-labeled answer.
toXiv_bot_toot

Third time this year: looking up the command in bash to detach a process from the terminal. #disown I will never learn enough.

🇺🇦 #NowPlaying on #BBC6Music's #RileyAndCoe
Julie Byrne:
🎵 Summer Glass
#JulieByrne
https://juliembyrne.bandcamp.com/track/summer-glass
https://open.spotify.com/track/1ZASawlvF4hnNZ15hlr8Ko

It’s Frighteningly Easy to Jailbreak Some Frontier AI Models
https://www.wired.com/story/jailbreaking-ai-models-google-anthropic-openai-spacexai/

A detailed recap of the White House's 19-day standoff with Anthropic, where a jailbreak dispute led officials to bluntly order Dario Amodei to take Fable down (Politico)
https://www.politico.com/news/magazine/2026/09/20/anthropic-white-house-ai-0108521…