Ben McCarty — security-maximalism 🛡️

Author | Inventor | Veteran | Cybersecurity Pro | Quantum R&D

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@RationalAnimat1 *𝙈𝙤𝙨𝙩 (ordinary) security measures would not work on superintelligence.

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@deanwball In terms of 'Probabilities', it is almost certain that "some stuff will go wrong". I am not sure we have a single example of a technology where nothing went wrong.
Some may argue that his 'Impact' severity of the Risk is too high, but seems reasonable considering the power of ASI

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@deanwball Some of the more mature organizations proactively develop defenses based on hypothetical threat modeling without waiting for an incident to happen
https://t.co/sw6Hfx6utu

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

So, vulnerable prototyping with no duty to security until incidents happen, which you will then iteratively patch in 'fixes' as an afterthought while increasing its risk until a government regulation steps in?
Black Swan events are not a "myth".
AI tech has new risks to manage.

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@allTheYud Mímir's wellspring

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@ESYudkowsky what about existentialist ethics?

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@boneGPT @SkyeSharkie Is refusing violence, suicide, and leaps of faith (religious or accelerationist) to instead lucidly struggle against possible AI-driven extinction not an honest way to live that takes some courage?

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@deanwball

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@So8res

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@liron @DavidDeutschOxf I wonder if the discovery of these zero-days revealed a novel class of weakness that expanded the existing CWE Dictionary, or did it simply find a new vulnerability based on an already-known weakness? Nicholas Carlini's talk on it chaining exploits may not be "true new knowledge"

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@boneGPT Keeping AI blind to time may be an important safety control to mitigate synchronized-coordination attacks and AI-based threats with chronological dependencies
Blocking access to clocks & even engineering randomized internal processing speeds of AI models may be needed to be safe

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@eurydicelives With some quantum mechanics added to the game, I feel a fighting chance to win against a superintelligence.

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@ESYudkowsky What do you think about Leibniz's Mill thought experiment?

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

https://t.co/rzZ2EF8Bfv

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

💡IDEA: a site like wikipedia - info on many subjects and created/edited by volunteers
.
..BUT it uses the ACH framework for controversial topics - encouraging viewpoints to collaboratively collect and document evidence inside the ACH

In theory it could be fairer & less biased

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@vitrupo Mutually Assured Dæmons

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@ESYudkowsky I am less familiar with your early work, but did it explore how to improve humanity in a safe, controlled, and reversible manner (assuming future technology made it feasible)?

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@RokoMijic What if the AI promises her that it would make some scientific breakthroughs and build some kind of sustainable ecological megaproject that achieves all of her goals?

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

Unofficial fan art I designed in tribute to "IF ANYONE BUILDS IT, EVERYONE DIES" - published today! Currently reading the book and enjoying it.

(Not affiliated, endorsed, or sponsored.)
#FanArt

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@danfaggella @AIHegemonyMemes A strangler fig supplants its host tree rather than succeeding it. The fig has its own flame of life, which carries on, but it is not our successor.
At first, the strangler fig appears to reinforce and strengthen the host tree of life, but ultimately causes its death.

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@danfaggella @AIHegemonyMemes What if it's a strangler fig tree? it still blooms, but kills the host tree of life...

[Ben McCarty — security-maximalism 🛡️ @apt_ben]

@danfaggella What if we could define & measure exactly what that special flame of humanity is? Then, carefully add to humanity's potentia, while still remaining human?

Basically, use AGI/ASI to solve the Sorites paradox, and keep adding to human's heap of potentia forever?