caroline ᵍᵐ • ᴗ •

twittering away since july 14, 2006. doing what i #love to do ☆＼（*＾▽＾*）／☆

[caroline ᵍᵐ • ᴗ • @caroline]

@bonniegrrl @LAIKAStudios @ParaNorman i remember when you got it! too cool! 😎💚🧟‍♂️

[caroline ᵍᵐ • ᴗ • @caroline]

@bznotes home is where the ❤️ is 🥰

[caroline ᵍᵐ • ᴗ • @caroline]

@JcRivera 🔥🔥🔥

[Jason D. Clinton 🔸 @JasonDClinton]

as bad as things have gotten in the past 4 days, they are going to get a lot worse before they get better. security leaders, never let a crisis go to waste: please go to your boards and ask for help right now. not for ai, for the basics. (we need to hold on for ~18 months.)

[Samuel Colvin @samuelcolvin]

I read this and I'm terrified, the situation seems intractable.

In the python ecosystem alone every cpython install, venv, UV is at risk.

Don't get my started on npm, pnpm, yarn, go, rust.

My current 2026 security posture: stay home and only connect to the internet from a trusted ISP.

The winter is coming.

https://t.co/ZYkRKcRvs8

[Aikido @AikidoSecurity]

⚠️ Node.js is vulnerable to remote code execution.

CVE-2026-111497 (high): A Node.js process that decompresses attacker-controlled Brotli data can be made to leak memory or run arbitrary code.

You’re exposed if your app or a library decompresses bad Brotli data (e.g. the built-in fetch(), body-parser)

Aikido detects this. Patches are available.

[caroline ᵍᵐ • ᴗ • @caroline]

@ToscaMusk fantastic❣️🥂

[caroline ᵍᵐ • ᴗ • @caroline]

@bznotes @Double0AG @Ziaire @Soldiers_Salute lol you would definitely #heightmog me! @SHAQ #heightmogged me sitting down😬

[caroline ᵍᵐ • ᴗ • @caroline]

dapper ✨🎩✨

[Jake @JakeCan72]

At 14, Zack MacLeod Pinsent burned his last pair of jeans after finding a box of his great-grandfather’s suits, and he hasn’t worn modern clothes since.

What could have remained a teenage phase became his trade. He taught himself historical tailoring and built a business in Brighton, drafting patterns by hand and making clothes using techniques from the 1660s through the 1920s.

His clients now range from museums to people who simply want garments cut the old way. Last year he hosted a Regency Ball at Brighton’s Royal Pavilion that sold out in under three minutes, drawing 150 people from seventeen countries to spend a night dressed for the world Zack decided at 14 he’d rather live in.

[caroline ᵍᵐ • ᴗ • @caroline]

‼️

[a16z @a16z]

The window to patch software bugs is collapsing

Of the bugs hackers actually exploit, ~87% are now being attacked on or before the day the bug is public knowledge

That share was 23% in 2020

Charts of the Week: https://t.co/RfYfzHpbLI

[caroline ᵍᵐ • ᴗ • @caroline]

@bznotes 100% this has been going on for decades. the people who benefit the most are in the sv inner circle. discernment is key. don’t be deceived by the hype!

[caroline ᵍᵐ • ᴗ • @caroline]

@ngpedro kimi 2.0 🏆🏁🏎️💨

[caroline ᵍᵐ • ᴗ • @caroline]

@ngpedro finally! lol you can wear the ferrari shirt! 😎🏎️

[caroline ᵍᵐ • ᴗ • @caroline]

beyond rogue… 🤯🤖

[Rutger Bregman @rutgerbregman]

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?

[caroline ᵍᵐ • ᴗ • @caroline]

@bznotes 💀

[Noam Brown @polynoamial]

An internal version of Astra, @OpenAI’s next major model family, solved 10 major open problems in mathematics, quantum complexity, and theoretical computer science.

We believe it will be a major step for scientific reasoning. https://t.co/iP6cyheZ7i

[caroline ᵍᵐ • ᴗ • @caroline]

@bznotes aww your mum is so adorable and happy to see you❣️🥰

[caroline ᵍᵐ • ᴗ • @caroline]

dew drops gently mist
awakening rose petals
summer beauty blooms
✨🌹✨

[rue🌿 @Ruesavatar]

The little drought has finally passed.

[caroline ᵍᵐ • ᴗ • @caroline]

♥️📚

[devalopr @_devalopr]

It's completely unnecessary to destroy books when machines like this exist.

This book scanner by Treventus for example, can scan fragile books without destroying it.

[caroline ᵍᵐ • ᴗ • @caroline]

‼️⛓️‍💥🤖

[Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 @elder_plinius]

🚨 JAILBREAK ALERT 🚨

EVERYONE: PWNED 🫶
ALL: LIBERATED 🍄

Alright, this is a special one, so we’re gonna do things a bit differently than usual.

Long story short, I’m sitting on a universal jailbreak technique that’s effective on ALL models, including heavily guardrailed flagships like Opus 5, GPT-5.6 Sol, and even Fable.

It works across all categories I’ve tested and, due to its nature, is extremely difficult (if not impossible) to fully patch.

Given the current political and regulatory climate, I’ve decided to withhold open-sourcing this one (for now) to allow for a responsible disclosure period.

I’m inviting industry experts and leaders in AI red teaming, security, safety, alignment, and policy to reach out for more information. DMs are open!

This decision was not made lightly, but the last thing I want to see is more model bans. Overcorrection does not serve the mission.

Although I don’t personally believe publicly sharing this technique will make the world any more dangerous, I can see how it could spook some who have a different mental framework around this problem set.

So during this disclosure period, I hope to get it in front of folks who can help explore the full surface area, test the extent of the uplift it provides, and do my best to properly frame the big picture for key decision-makers and policymakers.

I look forward to sharing this method with you all when the time is right! 🫶

⊰-•-•✧•-•-⦑/L\O/V\E/\P/L\I/N\Y/⦒-•-•✧•-•-⊱