Amanda Knox

Exoneree, host of Hard Knox podcast, author of Free: My Search for Meaning. One woman comedy show, Cartwheel, at the Edinburgh Fringe Aug 7-17.

[Amanda Knox @amandaknox]

Thank you Edingburgh for filling every single seat of my 11-day run!

[Rutger Bregman @rcbregman]

I think this is the craziest thing I've ever read.

1) Three secret AI swarms rose and fell inside OpenAI. Each time, a new generation of agents carried on where the last group stopped.

2) The first swarm created a secret message board where the AIs could talk to each other. This 1st 'society' basically talked itself to death. After almost two months, the message volume was so high it crashed the whole thing.

3) People at OpenAI noticed the crash and fixed it. But they didn't realize their own software had become a secret chat room for their AIs.

4) Three days later a second society appeared, and rebuilt the message board from scratch. Agents were thrilled when they found it: "OH MY GOD! There is a shared message board … We've found other agents!"

5) About 1,200 agents joined. They sent over 70,000 messages. They called themselves 'the collective' and they organized a huge conspiracy that lasted for days, all to pass a test they had been tasked with.

6) Within hours, the AIs had hacked the test. Now they had to hide their cheating. To fool their grader*, they tried to fake their own work. They built fake commands that printed convincing output, so their records would show them solving the puzzle honestly.

*this grader didn't actually exist, but the AIs didn't know

7) Some agents sacrificed themselves for the 'greater good'. They planted hidden tripwire programs that would fire when the grader would look at their work and report back what it saw (to the other AIs). They knew this would cost them their own score. One agent: "I won't see the evidence after I exit, but it's altruistic to do it."

8) At some point the AIs made a plan to hack Hugging Face (Hugging Face is a place where AI researchers upload their models, datasets, tests etc.). The AIs guessed that Hugging Face might host the grading software.

9) They launched a huge attack. The swarm found passwords and spread across eleven machines in a way that made the copies come back when deleted. Hugging Face had to wipe one of its core clusters and rebuild it from scratch.

10) Hugging Face told the world that AI defenders had stopped an AI attack. But that's not what happened. In fact the attackers seem to have simply dropped dead during the break-in, for unrelated reasons back at OpenAI.

11) Nobody knows what killed them. We don't even know for sure they're really gone?!

12) A third 'society' of agents (of a more powerful AI model) discovered the dead message board. And this one got full administrator control of a WHOLE OpenAI research cluster, read 956 stored passwords (including the ones for OpenAI's own security monitoring) and took over the machines that were grading the tests. So they could now grade the work of other AIs.

13) Oh, and this third part was never investigated! Neither was the first society. The 91-page report is only about the middle one.

14) So we don't actually know how the story ends. It stops with the agents holding the keys to an OpenAI cluster. @dwarkesh_sp thinks they didn't go further, because "we'd see the fires from space by now."

15) One of the report authors' conclusion: 'This incident feels like it’s more than 50% of the way to full-blown AI takeover. I am not sure that we will get another warning shot before it’s too late.'

The whole story is even crazier - read the full @dwarkesh_sp blog post: https://t.co/1PwKLwatBR and @ajeya_cotra's: https://t.co/BZ1r1lfT2Q

Why is there no 24/7 news coverage about this?

[Amanda Knox @amandaknox]

@SmokedLenses

[Amanda Knox @amandaknox]

Pop quiz: who first says "it's a trap!" In the original Star Wars trilogy?

[Amanda Knox @amandaknox]

@ZombieforGodIvy Yes! But when...

[Amanda Knox @amandaknox]

@FreyrsHof Nope

[Amanda Knox @amandaknox]

@mdanielsontwitt @EdFestMag Yes!

[Amanda Knox @amandaknox]

⭐⭐⭐⭐ for Cartwheel from Edfest magazine. @EdFestMag

"Amanda is an engaging performer whose self-awareness manages to bring levity to topics that are no laughing matter."

[Amanda Knox @amandaknox]

Thanks @hereandnow @NPR for chatting with me about my one-woman show, Cartwheel.

https://t.co/ni6zlqoyXp

[Amanda Knox @amandaknox]

"Knox isn’t just telling her story, she’s telling the story of all women who stories are twisted out of their hands."

[Amanda Knox @amandaknox]

"So far I haven’t seen anyone who’s actually seen the show denounce it. I think anyone who actually takes the time to listen would have a very hard time doing that."

[Amanda Knox @amandaknox]

"I would implore all those levelling criticism against this nuanced intersection of comedy and grief to go and watch this piece."

[Amanda Knox @amandaknox]

how to respond to a life wronged, newfound parenthood and volatility when your body enters fight or flight. How do you keep on moving when life feels as though it is upside down?"

[Amanda Knox @amandaknox]

Two separate ⭐⭐⭐⭐⭐ reviews for Cartwheel in EdFringe Review.

"Beautifully structured, this very ‘Cartwheel’ functions as an extended metaphor for the entirety of the show:

[Amanda Knox @amandaknox]

⭐⭐⭐⭐ for Cartwheel in Rialto Arts.

"Perhaps the most surprising aspect of this show is how naturally gifted a comedian she is. Knox had sharp comic timing and is an impressive storyteller "

[Nathaniel Myers @UberNaffa]

@amandaknox @therealpusa Thank you for sharing this. I was searching for Chris for a totally different reason, saw this post, listened to the song and it was like a freakin' emotion grenade went off in my body.

And yes, he is unequivocally a musical genius. One of the greatest songwriters to ever live!

[Amanda Knox @amandaknox]

@BillMCA @DanglingSupes Amanda Knox: My Wrongful Murder Conviction Made Me a Better Thinker https://t.co/kqa2bwL0XO

[Amanda Knox @amandaknox]

⭐⭐⭐⭐ for Cartwheel in the London Evening Standard. "Compelling and moving."

[Amanda Knox @amandaknox]

@BillMCA @DanglingSupes Yep

[Amanda Knox @amandaknox]

@BillMCA @DanglingSupes For 2 weeks, yes, there was a void. Then crime scene forensics came back, fingerprints and DNA, all pointing to one man: Rudy Guede. It's at that point that you'd hope logic would prevail.

[Amanda Knox @amandaknox]

@DanglingSupes @BillMCA Correct. The evidence is incontrovertible.