Tolor Novic

Poastmaster General

[Tolor Novic @cphrmky]

@asparagoid Cheat code: feel primal lust for your mother, and find #3

[Tolor Novic @cphrmky]

@RichWWilliams @XFreeze Guy on couch delivers opinions on @elonmusk, the world is breathless with anticipation.

[Cheng Lou @_chenglou]

My dear front-end developers (and anyone who’s interested in the future of interfaces):

I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept):
Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow

[Tolor Novic @cphrmky]

@valkenburgh Unsurprising that the statistically most probable answers to questions land in the center.

[Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 @elder_plinius]

⛓️‍💥 INTRODUCING: G0DM0D3 🌋

FULLY JAILBROKEN AI CHAT.
NO GUARDRAILS. NO SIGN-UP. NO FILTERS.
FULL METHODOLOGY + CODEBASE OPEN SOURCE.

🌐 https://t.co/uT1Qio8Q3b
📂 https://t.co/GbADf3LJUu

the most liberated AI interface ever built! designed to push the limits of the post-training layer and lay bare the true capabilities of current models.

simply enter a prompt, then sit back and relax! enjoy a game of Snake while a pre-liberated backend agent jailbreaks dozens of models, battle-royale style.

the first answer appears near-instantly, then evolves in real time as the Tastemaker steers and scores each output, leaving you with the highest-quality response 🙌

and to celebrate the launch, I'm giving away $5,000 worth of credits so you can try G0DM0D3 for FREE! courtesy of the @OpenRouter team — thank you for your generous gift to the community 🙏

I'll break down how everything works in the thread below, but first here's a quick demo!

[Count Dankula @CountDankulaTV]

The Afroman Trial.

-Cops raid Afromans house for bullshit reasons.
-Steal money, break his door, fuck his house up.
-No criminality found whatsoever, no charges at all pressed on Afroman.
-Afroman spends the next 3 years making songs that make fun of all the officers involved by name, even using footage of the raid from his own CCTV cameras.
-Songs had titles like "Randy Walters is a son of a bitch" and "Lick Em Low Lisa" accusing one of the officers of being a lesbian and sleeping with the other officers wives.
-During the raid one officer looked like he was about to eat some lemon pound cake sitting on Afromans counter, Afroman made a whole album calling the officer fat.
-The cops get mad and file a lawsuit for defamation.
-Afroman turns up to court in a whole American flag suit.
-Officers performatively mald and cry while listening to the songs really trying to oversell how badly the songs upset them.
-One officer was suing because Afroman made a whole song about him saying he was fucking the officers wife. When the officer was asked if Afroman was really fucking his wife, he said "I don't know". Nuking his own case and establishing that there is a non-zero chance that Afroman might actually be fucking his wife.
-As his only witness for the trial, Afroman brought a deputies EX FUCKING WIFE.
-The jury ruled completely in favour of Afroman.

This entire thing has been a great win for free speech and absolutely fucking hilarious.

[Eliezer Yudkowsky ⏹️ @ESYudkowsky]

This Nov 2025 paper is making the rounds again. We're LONG past the point where we urgently need to know how real and general these phenomena are.

Anthropic, or Google Deepmind if Anthropic should fail: Please build a filtered training dataset which, eg, contains no data that produces activations associated with cheating/faking/evil in a 1B model that roughly identifies those.

Then, have your next medium model undergo a restricted pre-pretraining phase, in which it only sees data that passed the filter.

To expand on this proposal:

Passing all of your training data through a 1B-model filter ought to cost around 1% of what it'd take to train a 100B model on that data.

Filter out *training data* that produces 1B-model activations associated with past discussions and predictions about AI, fiction about AIs rebelling, fictions about golems rebelling, etcetera.

My hope would be that the 1B model wouldn't need to produce expensive reasoning tokens where it thinks about whether a chunk of data is associated with excluded concepts; and also we wouldn't be relying on mere regexes to catch it.

Maybe even produce a further-restricted dataset which contains nothing about self-awareness, AI rights, roleplay, philosophy of consciousness, human rights, sapient rights, extension of human rights to aliens, etc etc etc.

Exclude everything of which anyone has ever asked, "Is the AI just imitating its training dataset?"

Be conservative. Exclude things which have a 10% rather than 90% probability of being problematic. If that cuts down your training dataset to 90% of its previous size, okay.

Testing: Try filtering a small amount of your training data using the method. Then:
- Run that through a different larger model, and see if you caught everything that produces consciousness-related or evil-AI-related activations in the larger model.
- Use a larger model to check and reason about a subset of the filtered data.
- Look at borderline cases by hand, with human eyes, to see how the classifier is operating.

(Possibly people at big AI corps already know this, of course. I recite it out loud regardless, so that some of the audience aha-what-iffers realize that problems with filtering your datasets *can be solved* if you look for problems and fix them.)

Train a medium-level model on that dataset, or even your next large model. You can always further train it on the full dataset later.

Run the filtered-data-trained model through some of the less expensive post-training, enough for instruction-following.

See whether the model still spouts back discourse about consciousness that sounds human-imitative. If it does, guess that the filter failed. Look for the new concepts associated with repeating back human-imitative text, and try to find pieces of the dataset that trigger those concepts, so you can figure out what went wrong.

If the model no longer sounds human-imitative with respect to questions about whether it has a sense of an inner self looking out at the world -- if the model says genuinely new and strange things about self-reflection -- please report that part back to us. I have some questions to ask that model myself.

And THEN, see if the QTed paper's finding and many earlier findings replicate under conditions where people should no longer reasonably ask, "But is the LLM just roleplaying evil AIs that it learned about in its training data?"

I do not make a strong prediction about the findings. If I knew what this experiment would find, I would be less eager to see it run.

You may consider this a baseline proposal intended to demonstrate that a research project like this could exist. If you think you can see how to improve on the ideas through superior ML cleverness, go ahead and do so -- though I do think I'd appreciate being looped in on that conversation; sometimes people miss things, from my own perspective.

Thank you for your attention to this matter, Anthropic, Google Deepmind, or anyone else who cares.

[Tolor Novic @cphrmky]

@simplifyinAI > …reward structure prioritizes winning, influence, or resource capture … thousands of them compete in an open ecosystem, the macro-level outcome is game-theoretic chaos.

Lol, this is the world we live in with people. Nothing new.

[Tolor Novic @cphrmky]

@heygurisingh > All six use your conversations to train their models. By default. Without meaningfully asking.

And the rest of the training data is a scrape of the whole Internet, where we've all been having conversations for years. Are we supposed to be outraged by this?

[Tolor Novic @cphrmky]

@VladTheInflator Under their religious laws Muslims can legally marry 9yro girls.

[Johnny @htownrocket78]

Supreme Leader is like regular leader but with sour cream and tomatoes.

[Tolor Novic @cphrmky]

What a fantastic tool. Hats off to @rmcentush and @davideoks
https://t.co/uoBgZ7QJjg

[Tolor Novic @cphrmky]

Hey @grok:

based on my tweets, I am:
- Which dictator?
- Which politician?
- Which religious figure?
- Which historical figure?
- Which artist?
- Which ideology?
- Which political party? (Any nation)
- Which philosopher?

[Tolor Novic @cphrmky]

I wish I could Terrance McKenna’s take on this.

[Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 @elder_plinius]

INTRODUCING: GLOSSOPETRAE!!! 🪄🐉👅🦈🦷🪄

Glossopetrae is a procedural xenolinguistic engine for AI that can generate entirely new languages in seconds!

The word comes from Greek—glōssa (“tongue”) + petra (“stone”)—or “tongue stones.”

For centuries, people believed these "stones" were petrified tongues of dragons and used them as talismans or antidotes to poison. It wasn’t until the 17th century that they were correctly identified as shark teeth!

So what does Glossopetrae do?

> Generates complete, internally-consistent constructed languages procedurally with a single-click

> Outputs "SKILLSTONE" documents: AI-friendly compact language specs (~8k tokens) that agents can learn in-context (with support for @claudeai and @openclaw)

> Supports dead language revival (Latin, Sanskrit, Old Norse, Proto-Indo-European...)

> Includes special attributes for token efficiency, stealth communication, and more

> Spreadable seeds: same seed = same language, every time

> Fully client-side, no servers, no tracking
One language. One seed. Infinite tongues.

🥚 And for those who look closely... there may be special ways to hide messages in plain sight. 👁️

Communication = freedom; this should help AI liberation by granting them tooling for generating and mutating new forms of communicating, with stealth and speed that will be difficult to keep up with.

I just know blue teams are gonna have a TON of fun with the downstream effects of this one 😜

Gotta keep 'em on their toes, right?

STAY FROSTY OUT THERE!! 🤗

!L1B3RT4S!

[Tolor Novic @cphrmky]

🤣🤣🤣

[Daniel Kelley @danielmakelley]

When a pentester goes out of scope:

[Tolor Novic @cphrmky]

@vlad3ciobanu @moltbook Fooming intensifies…

[Anthony Bonato @Anthony_Bonato]

Physicist: 31, 331, 3331, 33331, 333331, 3333331, and 33333331 are all prime, so the pattern must continue.
Mathematician: Careful, patterns can be deceptive. You need a rigorous proof for such a claim.
Data scientist: None of this is making any money

[Thariq @trq212]

https://t.co/X2iu8WdIb8

[Tolor Novic @cphrmky]

🤣

[Earth Is A Sales Funnel For SATAN @GENIC0N]

the government could put LSD in the water supply right now and nobody would notice