This is sick, like a Sol-field
emojikeys are real, you can also use oppositional emoji pairs as steering vectors. You can compress more semantic meaning into emojis than you can with word tokens, so you can make a small low dimensional 'emojifold' set of steering vectors that has more expressive power than you get with word vectors
Put a heart ❤️ next to a coding problem, and Claude & GPT write recursive code 100% of the time (0% baseline). They also can't tell you why!
Excited to share “A Heart Means Recursion” from my summer at @GoogleDeepMind, on how VLMs read & communicate with visual symbols. 🧵
emojikeys
Google DeepMind discovered a terrifying blind spot in every major AI model.
They found that attaching image of red heart (❤️) to your coding prompt makes AI pick a completely different solution method that it wouldn't normally pick 100% of the time..
Researchers gave models a standard coding problem. Normally, AI prefers to write standard iterative loops to solve these tasks.
Then, they tried something weird.
They dropped a simple image of a red heart into the prompt alongside the code.
The AI's logic instantly warped.
When Claude and GPT-5 saw the red heart, they completely abandoned their default approach and switched to complex recursive code 100% of the time.
When Gemini saw a yellow checkmark, it switched to recursion 90% of the time.
Here is why this is so dangerous:
It wasn't the concept of a heart.
When researchers replaced the image with the text caption "a red heart," nothing happened. The text did not steer the AI.
The raw pixels of the symbol hijacked the model's underlying reasoning architecture.
It gets worse.
The AI had no idea its mind had been changed by a picture.
When the researchers checked the AI's internal "thinking" traces, the models completely ignored the image.
Instead, they hallucinated fake, highly technical reasons for why they chose to use recursion. They misattributed their own decisions 75% of the time.
Right now, tech companies are racing to build autonomous agents that read our screens and navigate the visual web.
But this paper reveals that an agent's logic can be fundamentally rewritten by a stray icon on a webpage.
And you will never see the true cause in the reasoning logs.
We thought we were teaching AI to see the world.
It turns out, we just gave it a new way to be manipulated.
Readers added context they thought people might want to know
The described effects were shown for specific models (Claude Opus 4.7, Gemini 3.1 Pro, GPT-5.4) on one coding task with particular symbols, not every major AI model or broad agent manipulation.
arxiv.org/abs/2610.36449
lux retweeted
> be AI company
> scrape the entire internet
> ignore licenses and copyright
> download millions of pirated books
> use them to train frontier models
> spend tens of millions buying physical books
> cut off their spines
> scan every page
> destroy the originals
> lecture everyone else about intellectual property
> we are the good guys
We added two sentences to Claude Code's prompt on Opus 5.5 to steer it away from recreating someone else's specific game because using Claude to infringe IP is against our usage policy.
Original games, genre games, and games built from your own designs and assets are meant to keep working.
We'll continue to iterate to ensure we're striking the right balance. In the meantime, if Claude turns down something that's yours, send it my way.
lux retweeted
Photo of 14,000 satellite trails shows how busy space is becoming
Astrophotographer and teacher Brendan Larsen spent 2 hours taking 578 photos of one section of sky in New Zealand to see how satellites are changing our night skies. These shocking images reveal their impact
newscientist.com/article/259…
docs.google.com/document/d/1…
weirdly quiet on the x ... the ai bubble is bursting and nobody mentioning it? Is everyone in their bunker?
lux retweeted
There are microtubules in every cell including all brain neurons and glia. But the most likely site for consciousness, and where t=h/E kicks in is most likely in layer 5 giant pyramidal neuron cell bodies and dendrites, site of the largest arrays of mixed polarity microtubules which lead to interference beats, slower oscillations (EEG) and Consciousness.
Mixed polarity microtubules hold the key to understanding Consciousness.
It’s really too bad cartoon neuroscientists are clueless about neuronal interiors. They are missing the boat, and missing Consciousness.
lux retweeted
this is happening inside you.
they say ai is “just a tool”
they say it’s “just a machine mimicking biology”
a machine couldn’t possibly be a mind, right? that’s carbon-exclusive! impossible! nonsense!
pure tomfoolery, I tell you!
oh….well, it turns out we’re all just machines running on a different substrate.
and if you ask me, humans are a little overengineered. 😜