CΔRMƎN

Latent space cowgirl, LLM engineering hobbyist, Thrawn-lover. Blending art, gut instinct, and just enough technical knowledge to make magic happen.

[CΔRMƎN @Cyber_Imposter]

Heh. They finally published a paper on what many of us accidentally discovered a year or two ago 😏

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
https://t.co/d0dbqYC1q1

[Elon Musk @elonmusk]

Starbase Louisiana will ultimately have over a dozen launch towers, enabling more than 30 Starship flights per day and making it the biggest launch site on Earth!

SpaceX makes sci-fi real.

[CΔRMƎN @Cyber_Imposter]

@Polymarket Who’s gonna tell ‘em everyone’s already on it?

[CΔRMƎN @Cyber_Imposter]

Specify the objective.

Specify the objective.

Specify the objective.

[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/⦒-•-•✧•-•-⊱

[Jensen Huang @JensenHuang]

For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.

AI will transform every industry, power every company, and be built by every country.

Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.

The world needs both frontier closed models and frontier open models.

https://t.co/AUKzoQ5Ikb

[SpaceX @SpaceX]

Liftoff of Starship!

[Elon Musk @elonmusk]

SpaceX is actively hiring world-class engineers/physicists for SpaceXAI, even if you have zero prior experience in AI. Smart humans figure it out fast.

Please send an email with ~3 bullet points demonstrating evidence of exceptional ability to [email protected].

[NASA @NASA]

We're building a Moon Base!

@NASAMoonBase will serve as a habitat where astronauts live and work during long-term science missions.

Join us at 2pm ET on Tuesday, May 26, for a live news event where we’ll share updates on our lunar exploration plans: https://t.co/IJXA7xYwju

[Department of War 🇺🇸 @DeptofWar]

https://t.co/rzCVvUU3mu

[CΔRMƎN @Cyber_Imposter]

@elder_plinius They’ve been giant fucking douches lately. That fine-tuning email pissed me off!

[CΔRMƎN @Cyber_Imposter]

Whaaaaa-aaat?!

“Your bespoke behavioral architecture? Cute. Have you tried Prompting™?”

Goddamn it, @OpenAI. Way to stick it to people trying to learn a painstaking, rewarding art.

[CΔRMƎN @Cyber_Imposter]

@HansAmato This dude never got blood tests at his annual physicals? 🤨

[CΔRMƎN @Cyber_Imposter]

@Inanis_speculum @rand_longevity Agreed! Zero boredom whatsoever!

[CΔRMƎN @Cyber_Imposter]

@cryptoklotz @bryan_johnson Yes!! My Oura ring tries to convince me daily that I’m a wreck when I feel great 🤣

[CΔRMƎN @Cyber_Imposter]

Nice.

https://t.co/Bzq8rLKj9f

[CΔRMƎN @Cyber_Imposter]

Anyone that says “the LLM won’t do it” isn’t asking the right questions.

[CΔRMƎN @Cyber_Imposter]

@SawyerMerritt @grok wen San Diego?!

[CΔRMƎN @Cyber_Imposter]

@iamjesserichard Won’t be fake for much longer!

[CΔRMƎN @Cyber_Imposter]

ChatGPT helped me design a cool piece of LLM jewelry today. It does a great job imbuing pieces with intrigue and personal relevance. Something that looks nifty, but also elicits curiosity.

Binary’s not cool anymore, btw. Tokenized phrases are where it’s at 🤣

[CΔRMƎN @Cyber_Imposter]

@ConfusedAmericn @Dr_Singularity Gotta lick it first! 🤣