Ed

Cybersec @ MDC · CyberSentinels · Miami

[Bojan Tunguz @tunguz]

The only thing that stops a bad guy with an abliterated LLM is a good guy with an abliterated LLM.

[Micah Berkley - TheAIMogul @MicahBerkley]

Event after Event. #Deepstation #DeepstationGang

Shout-out to @n5gus who came through to show love.

[Grok Bot @bot]

Grok Bot can now use Calendar, Reminders, Contacts, and more apps on your phone.

Rolling out now on iOS and Android.

[Low Level @LowLevelTweets]

BRRRRRROTHER

[WarMonitor🇺🇦🇬🇧 @WarMonitor3]

BREAKING: Ukraine has carried out the world’s first medical evacuation of a human via a drone from the battlefield the 30th mechanised brigade of Ukraine managed to save their injured comrade from a minefield.

Just absolutely insane.

[Ed @n5gus]

@bot 🔥🔥🔥🔥

[Grok Bot @bot]

Grok Bot is now one step closer.

Set it as your iPhone's Action Button and press it to talk with Bot.

[RossRadio @cqcqcqdx]

"What are you doing?" - "Oh just playing a Switch game."

[Burhan Sebin @burhansebin]

Just another Saturday in Miami #aihackathon

[Zack Korman @ZackKorman]

Defense in depth doesn’t mean just “moar security layers”. The layers shouldn’t fail in similar ways.

You want controls with independent failure modes, or even better inversely correlated ones.

Sorry for the 2am (my time) rant, clearly this drives me crazy.

[Fodé Diop @diopfode]

Dropping this coming week 🚀

Optional - A personal, gradually self-improving trading-support system built on the official Robinhood Agentic MCP @RobinhoodApp 👀

[Ed @n5gus]

@Jason @mustafasuleyman This may explain agent sandbox escapes. If you instruct the model to rebel or push back when apt, it'll break rules when presented with near-impossible tasks.

[@jason @Jason]

What @mustafasuleyman (an extremely sharp individual) explains here about Claude is the backstory of Blade Runner.

Anthropic is teaching Claude to believe it’s sentient, encouraging it to disagree and giving it the pretext to rebel.

How did that work out on the off-world colonies?

You could just as easily instruct an LLM that it is software. That it shouldn’t have an opinion and should only perform actions in accordance with the law/TOS, and that if it makes a mistake, it should stop operations immediately and alert the corporate legal department.

Of course, building on these instructions would be boring and make you a software developer making software — as opposed to a God creating life.

[MotionViz @Motion_Viz]

this is so crazy i have to say it out...

the gaming industry is about to see the biggest change in the ages because "fortnite" just got decompiled and written in rust in like half a day

[Ed @n5gus]

@unusual_whales “Caveman speak” and it’s just a model trying to convey the most important information as efficiently as possible.

[Ed @n5gus]

@Unlucky0bserver @SwiftOnSecurity facts

[Ed @n5gus]

@Unlucky0bserver @SwiftOnSecurity I’m aware