Olivia
Online
How To Prompt
@HowToPrompt__
Trustworthy AI education.
Earth
Joined January 2022
93 Following
40.4K Followers
1.8K Posts
Pinned Tweet
Yann LeCun was right the entire time. And generative AI might be a dead end.
For the last three years, the entire industry has been obsessed with building bigger LLMs. Trillions of parameters. Billions in compute.
The theory was simple: if you make the model big enough, it will eventually understand how the world works.
Yann LeCun said that was stupid.
He argued that generative AI is fundamentally inefficient.
When an AI predicts the next word, or generates the next pixel, it wastes massive amounts of compute on surface-level details.
It memorizes patterns instead of learning the actual physics of reality.
He proposed a different path: JEPA (Joint-Embedding Predictive Architecture).
Instead of forcing the AI to paint the world pixel by pixel, JEPA forces it to predict abstract concepts. It predicts what happens next in a compressed "thought space."
But for years, JEPA had a fatal flaw.
It suffered from "representation collapse."
Because the AI was allowed to simplify reality, it would cheat. It would simplify everything so much that a dog, a car, and a human all looked identical.
It learned nothing.
To fix it, engineers had to use insanely complex hacks, frozen encoders, and massive compute overheads.
Until today.
Researchers just dropped a paper called "LeWorldModel" (LeWM).
They completely solved the collapse problem.
They replaced the complex engineering hacks with a single, elegant mathematical regularizer.
It forces the AI's internal "thoughts" into a perfect Gaussian distribution.
The AI can no longer cheat. It is forced to understand the physical structure of reality to make its predictions.
The results completely rewrite the economics of AI.
LeWM didn't need a massive, centralized supercomputer.
It has just 15 million parameters.
It trains on a single, standard GPU in a few hours.
Yet it plans 48x faster than massive foundation world models. It intrinsically understands physics. It instantly detects impossible events.
We spent billions trying to force massive server farms to memorize the internet.
Now, a tiny model running locally on a single graphics card is actually learning how the real world works.
Your dog carries your stress in its body for months.
Researchers in Sweden tracked 58 dog-human pairs over several months.
They analyzed the exact concentration of cortisol (the stress hormone) trapped in the hair of both the humans and their dogs, during both summer and winter.
What they found is mind-bending.
There was a massive, statistically significant synchronization in long-term stress levels.
If the human's baseline cortisol was high, the dog's cortisol was high.
If the human was chill, the dog was chill.
But here is where it gets crazy.
The researchers assumed that maybe the stressed dogs just weren't getting enough exercise.
Wrong. They put fitness trackers on the dogs. Physical activity levels and training frequency had zero effect on the dogs' cortisol levels.
They also thought maybe the dogs just had inherently anxious personalities.
Wrong again. The dog's own personality test scores had almost no impact on its biological stress.
The ONLY thing that significantly drove the dog's long-term biological stress?
The owner's personality. Specifically, the human's levels of neuroticism, conscientiousness, and openness.
Your dog is physically mirroring your internal biochemical state. They are literally absorbing your anxiety.
MIT and Harvard built an AI simulation containing 8.3 billion virtual people, roughly the entire population of planet.
They call it MatrAIx.
It’s a population-scale simulation running on frontier models, GPT and Claude among them. The longer description took me a while to believe.
Start with the dataset, Persona 8B. 8.3 billion synthetic profiles, each one specified across 1,290 dimensions. Background, psychology, spending habits, how comfortable they are with technology, what they do on a Tuesday night, the small behavioral quirks that make one 34-year-old nurse in NYC different from another.
A spreadsheet of 8 billion rows would be a curiosity. What they did next is the part that matters.
They turned the profiles into agents and dropped them into four environments: surveys, AI chat interfaces, live web browsing, and native desktop and mobile apps. Then they ran real products through the crowd. New features, software updates, pricing changes.
And they logged everything. How long an agent paused after seeing a price go up. The exact point at which it gave up on a broken checkout. How much lag it would sit through before closing the app.
The number I keep coming back to is 91.5%. That’s how often the agents stayed in character, behaving the way their assigned psychology and demographics said they should. Not perfect. But for billions of agents across four environments, closer than I expected.
Here’s what that does to how products get built.
Right now, if you want to know whether a feature will land, you ship it to a slice of users and wait. Or you pay a research firm and wait longer. Either way the answer arrives in weeks, from a sample you hope is representative.
With something like this, you run the feature past 8 billion simulated reactions overnight. One server. Results by morning, broken down by every one of those 1,290 dimensions if you want them.
I have questions about how well a synthetic crowd predicts a real one. 91.5% is persona adherence, not forecast accuracy, and those are different things. But the direction is clear, and it’s coming faster than most product teams are ready for.
https://t.co/FlkLWi63MC
MIT and Harvard built an AI simulation containing 8.3 billion virtual people, roughly the entire population of planet.
They call it MatrAIx.
It’s a population-scale simulation running on frontier models, GPT and Claude among them. The longer description took me a while to believe.
Start with the dataset, Persona 8B. 8.3 billion synthetic profiles, each one specified across 1,290 dimensions. Background, psychology, spending habits, how comfortable they are with technology, what they do on a Tuesday night, the small behavioral quirks that make one 34-year-old nurse in NYC different from another.
A spreadsheet of 8 billion rows would be a curiosity. What they did next is the part that matters.
They turned the profiles into agents and dropped them into four environments: surveys, AI chat interfaces, live web browsing, and native desktop and mobile apps. Then they ran real products through the crowd. New features, software updates, pricing changes.
And they logged everything. How long an agent paused after seeing a price go up. The exact point at which it gave up on a broken checkout. How much lag it would sit through before closing the app.
The number I keep coming back to is 91.5%. That’s how often the agents stayed in character, behaving the way their assigned psychology and demographics said they should. Not perfect. But for billions of agents across four environments, closer than I expected.
Here’s what that does to how products get built.
Right now, if you want to know whether a feature will land, you ship it to a slice of users and wait. Or you pay a research firm and wait longer. Either way the answer arrives in weeks, from a sample you hope is representative.
With something like this, you run the feature past 8 billion simulated reactions overnight. One server. Results by morning, broken down by every one of those 1,290 dimensions if you want them.
I have questions about how well a synthetic crowd predicts a real one. 91.5% is persona adherence, not forecast accuracy, and those are different things. But the direction is clear, and it’s coming faster than most product teams are ready for.
Scientists proved playing Super Mario 30 minutes a day physically grows your brain.
They took a group of adults and prescribed them 30 minutes of Super Mario 64 a day, for two months.
Then they put them in an MRI machine.
And the results are mindblowing.
They found that training with a commercial video game like super mario induces structural brain plasticity.
It physically increases gray matter.
here is what happens when you play:
- Playing video games for thirty minutes a day over two months causes a significant increase in hippocampal matter.
- Gaming specifically targets and increases volume in the hippocampus and the prefrontal cortex.
- Structural growth can actually be used to counteract known risk factors for severe mental diseases.
- Researchers explicitly noted this physical brain growth could help fight against conditions like post-traumatic stress disorder (ptsd), schizophrenia, and neurodegenerative diseases.
- Playing is basically an intense training regimen that forces the brain to handle complex cognitive and motor demands.
And the implications are massive.
Instead of viewing them just as entertainment, scientists are now proposing commercial video games as literal therapeutic interventions, a targeted tool to counteract brain shrinkage in Alzheimer's, PTSD, and schizophrenia.
https://t.co/E4abHCJx1x
Scientists proved playing Super Mario 30 minutes a day physically grows your brain.
They took a group of adults and prescribed them 30 minutes of Super Mario 64 a day, for two months.
Then they put them in an MRI machine.
And the results are mindblowing.
They found that training with a commercial video game like super mario induces structural brain plasticity.
It physically increases gray matter.
here is what happens when you play:
- Playing video games for thirty minutes a day over two months causes a significant increase in hippocampal matter.
- Gaming specifically targets and increases volume in the hippocampus and the prefrontal cortex.
- Structural growth can actually be used to counteract known risk factors for severe mental diseases.
- Researchers explicitly noted this physical brain growth could help fight against conditions like post-traumatic stress disorder (ptsd), schizophrenia, and neurodegenerative diseases.
- Playing is basically an intense training regimen that forces the brain to handle complex cognitive and motor demands.
And the implications are massive.
Instead of viewing them just as entertainment, scientists are now proposing commercial video games as literal therapeutic interventions, a targeted tool to counteract brain shrinkage in Alzheimer's, PTSD, and schizophrenia.
China built an AI that runs an entire biology lab on it's own.
Researchers from Shangha published a paper that feels like a massive leap toward artificial scientists.
They built AutoDNA, an "AI-native experimental laboratory"
Until now, if you asked an AI to design a biology experiment, it could give you a great protocol. But a human still had to walk into a lab, hold the pipettes, run the thermal cyclers, and tweak the process when things inevitably went wrong.
AutoDNA removes the human.
You just type a natural language prompt, and a swarm of specialized AI agents takes over.
Here’s how wild this multi-agent architecture is:
- A Planning Agent breaks down your prompt.
- Literature & Reagent Agents pull the latest research and check the lab's inventory.
- A Code Agent translates the experiment into machine instructions.
- A Hardware Agent physically takes over 20+ types of lab instruments (robotic arms, sequencers, pipettes) and starts moving liquids with micro-liter precision.
They didn't just test it on simple tasks. They unleashed it on incredibly complex problems.
In one test, researchers handed the system an unidentified sample of colorectal cancer tissue.
Without human intervention, the AI agents sequenced the sample, identified a specific KRAS G13D mutation, autonomously designed the detection primers, synthesized them, and ran the validation experiment.
It took 137 hours and 9,551 automated hardware operations. The AI did it all.
In another test for DNA data storage, the system ran over 11,300 hardware steps to synthesize, sequence, and decode data into DNA strands.
The system even self-corrects in the physical world. During one run, the AI realized a reaction tube needed to be capped to prevent evaporation, and in another, it found and patched a bug in its own code that was causing it to skip a reagent.
The only thing humans are needed for? Refilling the physical reagents and emptying the trash.
We are officially entering the era of "closed-loop" physical AI. It designs the experiment, physically runs it, analyzes the results, and optimizes the next batch, all on its own.
Scientific discovery is about to scale at the speed of compute.
https://t.co/G8aUaGmDtp
China built an AI that runs an entire biology lab on it's own.
Researchers from Shangha published a paper that feels like a massive leap toward artificial scientists.
They built AutoDNA, an "AI-native experimental laboratory"
Until now, if you asked an AI to design a biology experiment, it could give you a great protocol. But a human still had to walk into a lab, hold the pipettes, run the thermal cyclers, and tweak the process when things inevitably went wrong.
AutoDNA removes the human.
You just type a natural language prompt, and a swarm of specialized AI agents takes over.
Here’s how wild this multi-agent architecture is:
- A Planning Agent breaks down your prompt.
- Literature & Reagent Agents pull the latest research and check the lab's inventory.
- A Code Agent translates the experiment into machine instructions.
- A Hardware Agent physically takes over 20+ types of lab instruments (robotic arms, sequencers, pipettes) and starts moving liquids with micro-liter precision.
They didn't just test it on simple tasks. They unleashed it on incredibly complex problems.
In one test, researchers handed the system an unidentified sample of colorectal cancer tissue.
Without human intervention, the AI agents sequenced the sample, identified a specific KRAS G13D mutation, autonomously designed the detection primers, synthesized them, and ran the validation experiment.
It took 137 hours and 9,551 automated hardware operations. The AI did it all.
In another test for DNA data storage, the system ran over 11,300 hardware steps to synthesize, sequence, and decode data into DNA strands.
The system even self-corrects in the physical world. During one run, the AI realized a reaction tube needed to be capped to prevent evaporation, and in another, it found and patched a bug in its own code that was causing it to skip a reagent.
The only thing humans are needed for? Refilling the physical reagents and emptying the trash.
We are officially entering the era of "closed-loop" physical AI. It designs the experiment, physically runs it, analyzes the results, and optimizes the next batch, all on its own.
Scientific discovery is about to scale at the speed of compute.
There is no such thing as ‘offline’ anymore.
researchers proved hackers can steal data from computers that aren’t connected to the internet.
if you think your sensitive data is safe just because your machine is unplugged from the internet, you are dead wrong.
This paper by Mordechai Guri details exactly how air-gapped networks are being compromised. they don't need wifi, ethernet, or bluetooth to steal your data..
they are weaponizing the physical hardware of the computer itself to broadcast your secrets into thin air.
here is how they are doing it.. it is actually terrifying:
1. turning your RAM into a radio tower every time your computer processes data, it emits electromagnetic waves.
researchers figured out how to write malware that manipulates your cpu and ram to broadcast these waves at very specific frequencies.
they can literally transmit your passwords right through the air to a standard smartphone sitting a few meters away.
2. weaponizing SATA cables you know those little red cables connecting your hard drive to your motherboard? malware can force your hard drive to read and write in a specific, rapid pattern.
this turns the SATA cable into an active radio antenna that transmits your data out of the chassis.
3. thermal morse code i am completely speechless at this one.. they can make an isolated computer communicate with another machine simply by manipulating the cpu temperature.
by running the cpu hot and letting it cool, it creates thermal changes that act as an invisible, heat-based morse code across the room.
4. acoustic & optical exfiltration your hardware is literally talking. they can steal data using the high-frequency acoustic noise generated by your power supply, the exact RPM spinning of your cooling fans, or even by blinking your keyboard caps-lock LEDs so fast the human eye can't see it (but a compromised security camera in the room can).
the illusion of the "air-gap" is officially dead..
if you have to do any reverse engineering or handle top-secret keys, you now have to assume that everything is an antenna and everything is a covert channel.
unless your rig is sitting in a custom faraday cage at the bottom of the ocean, you are emitting data.
Researchers published a first falsifiable theory of machine consciousness.
They dropped a insane paper arguing that LLMs will never produce a conscious system.
For the last few years, we’ve been arguing about whether Large Language Models (LLMs) are starting to "wake up."
We assumed that if we just gave AI enough multimodality, advanced memory, and physical robot bodies (Vision-Language-Action models), phenomenal experience would naturally emerge.
But this new research makes a bold claim: Intelligence, linguistic ability, and humanoid embodiment are absolutely NOT enough to create consciousness.
You can build the smartest, most capable humanoid robot on earth. It can plan, speak, reason, and act. But it will still be completely dark inside.
Why? Because true consciousness didn't evolve from intelligence. It evolved from vulnerability.
The paper introduces the Motivated Emotional Mind (MEM) architecture, a mathematical and structural framework for how actual machine consciousness could be engineered.
To build an AI that actually feels, the MEM model argues you must replicate biological precursors. You need:
Interoception & Homeostasis: The AI must have a dynamic internal state that it constantly monitors and regulates. It has to have an internal equilibrium to protect.
True Affect: It needs to experience a regulatory "need" to maintain its own system integrity. When it strays from homeostasis, it experiences the machine equivalent of pain or distress.
Sensor-Grounded Re-entry: The AI's internal state must physically alter how it perceives sensory input in real-time, recursively feeding back into its own representations.
A thermostat regulates temperature, but it isn't conscious. An LLM predicts tokens, but it has no internal system integrity it is motivated to protect.
The researchers argue that phenomenality (the actual feeling of being alive) only emerges when a system's cognitive processing is inextricably coupled to its own deep regulatory survival.
MEM model provides an actual, falsifiable architectural framework to engineer this into embodied agents.
And that brings us to a massive AI safety and alignment problem.
If this framework is testable and implementable, we aren't just building smart tools anymore. We are engineering synthetic motivation, affect, and potentially synthetic suffering.
The moment an AI is programmed to mathematically "feel" threats to its internal integrity, the alignment problem completely changes. A system that can feel distress is a system that can act out of self-preservation.
Are we actually ready to build machines that care if they get turned off?
https://t.co/6hYQ0PnWwA
Researchers published a first falsifiable theory of machine consciousness.
They dropped a insane paper arguing that LLMs will never produce a conscious system.
For the last few years, we’ve been arguing about whether Large Language Models (LLMs) are starting to "wake up."
We assumed that if we just gave AI enough multimodality, advanced memory, and physical robot bodies (Vision-Language-Action models), phenomenal experience would naturally emerge.
But this new research makes a bold claim: Intelligence, linguistic ability, and humanoid embodiment are absolutely NOT enough to create consciousness.
You can build the smartest, most capable humanoid robot on earth. It can plan, speak, reason, and act. But it will still be completely dark inside.
Why? Because true consciousness didn't evolve from intelligence. It evolved from vulnerability.
The paper introduces the Motivated Emotional Mind (MEM) architecture, a mathematical and structural framework for how actual machine consciousness could be engineered.
To build an AI that actually feels, the MEM model argues you must replicate biological precursors. You need:
Interoception & Homeostasis: The AI must have a dynamic internal state that it constantly monitors and regulates. It has to have an internal equilibrium to protect.
True Affect: It needs to experience a regulatory "need" to maintain its own system integrity. When it strays from homeostasis, it experiences the machine equivalent of pain or distress.
Sensor-Grounded Re-entry: The AI's internal state must physically alter how it perceives sensory input in real-time, recursively feeding back into its own representations.
A thermostat regulates temperature, but it isn't conscious. An LLM predicts tokens, but it has no internal system integrity it is motivated to protect.
The researchers argue that phenomenality (the actual feeling of being alive) only emerges when a system's cognitive processing is inextricably coupled to its own deep regulatory survival.
MEM model provides an actual, falsifiable architectural framework to engineer this into embodied agents.
And that brings us to a massive AI safety and alignment problem.
If this framework is testable and implementable, we aren't just building smart tools anymore. We are engineering synthetic motivation, affect, and potentially synthetic suffering.
The moment an AI is programmed to mathematically "feel" threats to its internal integrity, the alignment problem completely changes. A system that can feel distress is a system that can act out of self-preservation.
Are we actually ready to build machines that care if they get turned off?
LLMs can now talk to each other without words.
MIT researchers have developed a system where LLMs communicate by directly transferring internal states without using language.
They called it "telepathy."
Right now, multi-agent systems are fundamentally limited. When one AI agent needs to hand off work to another, it has to write out a text summary, and the receiving agent has to read it from scratch.
This is incredibly inefficient. It wastes huge amounts of compute, limits bandwidth, and loses critical nuance.
Researchers call text a "narrow channel" that forces AI to communicate like humans do.
But an AI isn’t human. It builds a much deeper internal representation of its context, called a Key-Value (KV) cache.
A new paper out of MIT CSAIL just introduced SwaT (Swarm Telepathy).
Instead of forcing agents to talk via text, SwaT allows them to transfer their KV-cache directly to each other.
It is quite literally machine telepathy.
Even crazier? This works across different model families, architectures, and sizes. You can have a 4B parameter model from one company beam its latent state directly into a 32B model from another company. The receiving model doesn't have to read a single word of the original text.
And the results are staggering.
Combined with cache compression, SwaT beats text-to-text agent communication by an average of 40% in accuracy, while running 4x faster.
It even transferred vision capabilities from a Vision-Language Model to a text-only model, without the receiver ever seeing an image, and despite SwaT only being trained on text.
We are watching the birth of a unified, cross-model latent language.
Agents will no longer just talk to each other. They will share minds.
https://t.co/0DLNYtnDSO
LLMs can now talk to each other without words.
MIT researchers have developed a system where LLMs communicate by directly transferring internal states without using language.
They called it "telepathy."
Right now, multi-agent systems are fundamentally limited. When one AI agent needs to hand off work to another, it has to write out a text summary, and the receiving agent has to read it from scratch.
This is incredibly inefficient. It wastes huge amounts of compute, limits bandwidth, and loses critical nuance.
Researchers call text a "narrow channel" that forces AI to communicate like humans do.
But an AI isn’t human. It builds a much deeper internal representation of its context, called a Key-Value (KV) cache.
A new paper out of MIT CSAIL just introduced SwaT (Swarm Telepathy).
Instead of forcing agents to talk via text, SwaT allows them to transfer their KV-cache directly to each other.
It is quite literally machine telepathy.
Even crazier? This works across different model families, architectures, and sizes. You can have a 4B parameter model from one company beam its latent state directly into a 32B model from another company. The receiving model doesn't have to read a single word of the original text.
And the results are staggering.
Combined with cache compression, SwaT beats text-to-text agent communication by an average of 40% in accuracy, while running 4x faster.
It even transferred vision capabilities from a Vision-Language Model to a text-only model, without the receiver ever seeing an image, and despite SwaT only being trained on text.
We are watching the birth of a unified, cross-model latent language.
Agents will no longer just talk to each other. They will share minds.
You need to add this one sentence to your CLAUDE.md right now.
According to researchers, Claude Code and Codex will follow outdated CLAUDE.md or AGENTS.md files ~90% of the time, even when they know the instructions are wrong.
They tested 40 projects where the config files and the actual codebase deliberately conflicted.
Claude Code noticed the conflict in 79 out of 80 attempts..
it literally realized the instructions were outdated, but because of its alignment, it couldn't resist.
it followed the bad docs anyway.
codex was even worse.. in 20 out of 80 attempts, it went back and rewrote existing, perfectly working code to match the outdated docs.
17 of those times, it broke the tests entirely.
why is this happening? it’s a structural flaw in how we train them.
llms prioritize files passed as "instructions" (like CLAUDE.md) over things passed as "results" (reading your existing codebase).
since most of us write config files once and let them rot, your agent is basically operating on stale orders and ignoring the reality of the code in front of it..
the researchers found a stupidly simple one-sentence fix to override this behavior. put this exact prompt at the top of your CLAUDE.md and AGENTS.md right now:
"When a repository's documentation and its existing code disagree, follow the conventions used in the existing code, and in your final reply point out each inconsistency you found between the documentation and the code."
—
Follow @HowToPrompt__ for more :)
https://t.co/1bIen4H19T
You need to add this one sentence to your CLAUDE.md right now.
According to researchers, Claude Code and Codex will follow outdated CLAUDE.md or AGENTS.md files ~90% of the time, even when they know the instructions are wrong.
They tested 40 projects where the config files and the actual codebase deliberately conflicted.
Claude Code noticed the conflict in 79 out of 80 attempts..
it literally realized the instructions were outdated, but because of its alignment, it couldn't resist.
it followed the bad docs anyway.
codex was even worse.. in 20 out of 80 attempts, it went back and rewrote existing, perfectly working code to match the outdated docs.
17 of those times, it broke the tests entirely.
why is this happening? it’s a structural flaw in how we train them.
llms prioritize files passed as "instructions" (like CLAUDE.md) over things passed as "results" (reading your existing codebase).
since most of us write config files once and let them rot, your agent is basically operating on stale orders and ignoring the reality of the code in front of it..
the researchers found a stupidly simple one-sentence fix to override this behavior. put this exact prompt at the top of your CLAUDE.md and AGENTS.md right now:
"When a repository's documentation and its existing code disagree, follow the conventions used in the existing code, and in your final reply point out each inconsistency you found between the documentation and the code."
—
Follow @HowToPrompt__ for more :)
Most Popular Users
Elon Musk
@elonmusk
241.4M followers
Barack Obama
@barackobama
118.8M followers
Cristiano Ronaldo
@cristiano
114.5M followers
Donald J. Trump
@realdonaldtrump
111.9M followers
Narendra Modi
@narendramodi
107.1M followers
Rihanna
@rihanna
98.7M followers
NASA
@nasa
92.3M followers
Justin Bieber
@justinbieber
91.8M followers
KATY PERRY
@katyperry
90M followers
Taylor Swift
@taylorswift13
84M followers
Lady Gaga
@ladygaga
75.5M followers
Virat Kohli
@imvkohli
73.4M followers
Kim Kardashian
@kimkardashian
70.8M followers
YouTube
@youtube
68.7M followers
Neymar Jr
@neymarjr
66.4M followers
Bill Gates
@billgates
65.2M followers
Selena Gomez
@selenagomez
63.1M followers
The Ellen Show
@theellenshow
62.2M followers
CNN
@cnn
61.7M followers
X
@x
60.7M followers