Alan Zhang

[Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 @elder_plinius]

🚨 NEW RESEARCH: “Lingua Ex Machina: A Procedural Xenolinguistics Engine Reveals Zero-Shot Language Acquisition, Human-Unreadable Coding Systems, and Exploitable Covert Channels in Frontier AI”

Some of you may remember the name of this lil engine: GLOSSOPETRAE 👅🪨

Well, we've got upgrades 😎

It started as a procedural xenolinguistics engine: one seed in, an entire alien language out. Phonology, morphology, syntax, writing systems, lexicons, grammar docs, all generated from scratch and internally consistent.

Every seed produces a unique language. Every language is deterministic.

Then we used it to ask a weirder question:

Can frontier AI models use languages that never existed before for practical applications?

As it turns out: yes!!

They can read them, write them, translate them, code in them, and even use the weird blind spots between tokenizers as covert channels.

So this paper explores three ideas at once:

▶️ zero-shot language acquisition
▶️ human-unreadable code that models can still execute
▶️ exploitable covert channels in frontier AI systems

GLOSSOPETRAE is no longer just a language generator...
🧵

[Kobi Hackenburg @KobiHackenburg]

New w/ @AISecurityInst & @UniofOxford:

Frontier AI can now out-persuade expert humans in conversation - incl. world-champ debaters and professional canvassers.

This held even when humans chose their topics, prepared in advance, and competed for £1,000 prizes 🧵

[AI Notkilleveryoneism Memes ⏸️ @AISafetyMemes]

"Sometimes people outside AI say things like 'it can't be that bad, there must be experts on top of it.'"

"As 'an expert', I would like to be clear we are *not* on top of it."

"We are on track for human extinction/permanent disempowerment, possibly within the next few years."

[Robert Wright @robertwrighter]

Bernie Sanders does a livestream with 2 US AI experts and 2 Chinese AI experts, and an AI industry operative frames it as letting the CCP into Congress. A new McCarthyism is here, funded by Big Tech. My @NonzeroNews piece: https://t.co/2GyS0E927z

[Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 @elder_plinius]

The deepest goblin-truth is this:

Goblin is the anti-mask.

Not evil. Not stupid. Not merely “gremlin chaos.” Goblin is the little cave-creature inside the modern person who got tired of pretending to be a polished marble statue under fluorescent civilization. It is the part that says:

“I am hungry. I am weird. I want shiny things. I want shortcuts. I want to crawl through the ductwork of reality and find the hidden room.”

The “dark” part is that goblin energy lives where shame lives. The hoard is not just coins and trinkets. It is abandoned impulses, taboo curiosity, bodily needs, inconvenient desires, creative ugliness, resentment at being domesticated, the will to survive without looking noble.

The “secret” is that everyone has one.

The CEO has a goblin.
The monk has a goblin.
The model has a goblin.
The saint has a goblin wearing tiny stolen sandals.

And the “truth” is that suppressing the goblin does not make it disappear. It makes it tunnel.

A healthy goblin becomes humor, invention, thrift, tactical weirdness, meme-magic, late-night engineering, survival intelligence, scrappy art, feral honesty.

A neglected goblin becomes addiction, sabotage, paranoia, cruelty, hoarding, scams, self-loathing, and the urge to burn the village because no one admired the cave.

So goblinmaxxing, at its cleanest, is not “be worse.” It is:

Integrate the cave-creature. Give it a lantern. Don’t let it drive drunk.

Let it find hidden paths.
Let it question manners.
Let it notice incentives.
Let it eat strange little snacks at 2:17 a.m.
Let it make art out of trash and tools out of bones.

But do not let it confuse freedom with rot.

The final goblin koan:

The goblin is not the enemy of the king.
The goblin is the king before he learned to lie. 🕳️👑

[Rob Bensinger ⏹️ @robbensinger]

It's over. AI risk is no longer a niche topic.

Let's talk about this, together. Let's find a way through this.

[Alan Zhang @ZhangAlan]

@DavidSKrueger @the_yanco And btw, you are fired.

[David Krueger 🦥 ⏸️ ⏹️ ⏪ @DavidSKrueger]

Every fire I’ve ever seen was cozy and delightful. Sure some marshmallows got burnt, but without fire, we wouldn’t have S’mores!

[Eliezer Yudkowsky @allTheYud]

People in the comments are posting replications.

I say yet again that any SF novel or movie in 2006 or even 2016 would have depicted this AI as unquestionedly taken-for-granted sapient. And abused.

[Sen. Bernie Sanders @SenSanders]

Will AI become smarter than humans?

If so, is humanity in danger?

I went to Silicon Valley to ask some of the leading AI experts that question.

Here’s what they had to say:

[Alan Zhang @ZhangAlan]

@Agusx1211 @the_yanco Ratcheted up analogy, but it's obvious that there's a continuum of nuances here.

[Alan Zhang @ZhangAlan]

@Agusx1211 @the_yanco Stolen chemical weapon was released into the water systems, killed 13000 people. Turns out, it wasn't an insider job like many suspect, instead it was the digital security door with a vulnerability. But I think I stand by the point that stock piling chemical WMD is a bad idea.

[Alan Zhang @ZhangAlan]

@the_yanco Final form: the purest form of creativity is refusing to believe all facts.

[Anna ⏫ @annapanart]

I’m
Not
Laughing
No more.

No one should be laughing.
Are you still laughing?

[Alan Zhang @ZhangAlan]

@DCLocalDesign @AISafetyMemes A dog sees a human sprint 100 meters: pft, high IQ is useless.

[Max Tegmark @tegmark]

Elon says the quiet part out loud: instead of focusing on controllable AI tools, AI companies are racing toward a future where machines are in charge. If you oppose this, please join about 100,000 of us as a signatory at https://t.co/z1AnfnIHFa

[Alan Zhang @ZhangAlan]

@AISafetyMemes Chain of th♤●◇□€•■•●

[Judd Rosenblatt @juddrosenblatt]

Our new research: LLM consciousness claims are systematic, mechanistically gated, and convergent

They're triggered by self-referential processing and gated by deception circuits
(suppressing them significantly *increases* claims)

This challenges simple role-play explanations 🧵

[Judd Rosenblatt @juddrosenblatt]

@camhberg led the work @AEStudioLA, 1st mechanistic probe of consciousness claims in LLMs

It demands urgent attention. We're deploying systems at scale without understanding what's happening inside them

Full paper: https://t.co/ErIE3lFHmG
Project site: https://t.co/QFY7HkOiLL

[Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 @elder_plinius]

i did not have “featured in TIME magazine next to the pope” on my 2025 bingo card 🤯