The Transcript
RT @TheTranscript_: $RBLX CEO: "Every day, we capture roughly 30,000 years of human interaction data on Roblox in a PII and privacy compliant way. We're actively using this data to develop and train AI models that continue to bring our vision to life. I want to highlight that we're internally now running over 400 AI models. "
tweet
RT @TheTranscript_: $RBLX CEO: "Every day, we capture roughly 30,000 years of human interaction data on Roblox in a PII and privacy compliant way. We're actively using this data to develop and train AI models that continue to bring our vision to life. I want to highlight that we're internally now running over 400 AI models. "
tweet
Offshore
Video
memenodes
Who got you into crypto?
Thanks to them you’re going to die 10 years younger from stress and bad habits https://t.co/jkBnOI0EP1
tweet
Who got you into crypto?
Thanks to them you’re going to die 10 years younger from stress and bad habits https://t.co/jkBnOI0EP1
tweet
Offshore
Video
memenodes
I can see why they used up all the condoms in the olympic village https://t.co/lRcnJaByRz
tweet
I can see why they used up all the condoms in the olympic village https://t.co/lRcnJaByRz
tweet
Offshore
Video
memenodes
RT @naiivememe: the refrigerator since 2018 watching me turn off the TV to let it rests
https://t.co/tJH4DFN3KP
tweet
RT @naiivememe: the refrigerator since 2018 watching me turn off the TV to let it rests
https://t.co/tJH4DFN3KP
tweet
Javier Blas
"Global oil prices have not declined despite a global surplus," says Goldman Sachs. "One key reason for this disconnect is that much of this global surplus has materialized as rising inventories of sanctioned crude "stuck at sea" while OECD stocks in pricing centers have remained stable."
tweet
"Global oil prices have not declined despite a global surplus," says Goldman Sachs. "One key reason for this disconnect is that much of this global surplus has materialized as rising inventories of sanctioned crude "stuck at sea" while OECD stocks in pricing centers have remained stable."
tweet
Offshore
Photo
God of Prompt
🚨 Holy shit… Google just published one of the cleanest demonstrations of real multi-agent intelligence I’ve seen so far.
Not another “look, two chatbots are talking” demo.
An actual framework for how agents can infer who they’re interacting with and adapt on the fly.
The paper is “Multi-agent cooperation through in-context co-player inference.”
The core idea is deceptively simple:
In multi-agent environments, performance doesn’t just depend on the task.
It depends on who you’re paired with.
Most current systems ignore this.
They optimize against an average opponent.
Or assume fixed partner behavior.
Or hard-code roles.
Google does something smarter.
They let the model infer its co-player’s strategy directly from the interaction history inside the context window.
No retraining, separate belief model and no explicit opponent classifier.
Just in-context inference.
The agent observes a few rounds of behavior. Forms an implicit hypothesis about its partner’s type. Then updates its own strategy accordingly.
This turns static policies into adaptive ones.
The experiments are structured around cooperative and social dilemma games where partner types vary:
Some partners are fully cooperative.
Some are selfish.
Some are stochastic.
Some strategically defect.
Agents without co-player inference treat all partners the same.
Agents with inference adjust.
And the performance gap is significant.
What makes this paper uncomfortable for a lot of current “multi-agent” hype is how clearly it shows what real coordination requires.
First, coordination is not just communication. It’s modeling the incentives and likely actions of others.
Second, robustness matters. An agent that cooperates blindly gets exploited. An agent that defects blindly loses cooperative gains. The system must dynamically balance trust and caution.
Third, adaptation must happen at inference time. In real deployments, you cannot retrain every time the population changes.
The most interesting part is that this capability emerges purely from structured context.
The model isn’t fine-tuned to classify opponent types explicitly. It uses behavioral traces embedded in the prompt to infer latent strategy.
That’s belief modeling through language.
And it scales.
Think about where this matters outside toy games:
Autonomous trading systems reacting to different market participants.
Negotiation agents interacting with unpredictable humans.
Distributed AI workflows coordinating across departments.
Swarm robotics where teammate reliability varies.
In all these settings, static competence is not enough.
Strategic awareness is the bottleneck.
The deeper shift is philosophical.
We’ve been treating LLM agents as isolated optimizers.
This paper moves us toward agents that reason about other agents reasoning about them.
That’s recursive modeling.
And once that loop becomes stable, you no longer have “a chatbot.”
You have a participant in a strategic ecosystem.
The takeaway isn’t that multi-agent AI is solved.
It’s that most current systems aren’t even attempting the hard part.
Real multi-agent intelligence isn’t multiple prompts in parallel.
It’s adaptive belief formation under uncertainty.
And this paper is one of the first clean proofs that large models can do that using nothing but context.
Paper: Multi-agent cooperation through in-context co-player inference
tweet
🚨 Holy shit… Google just published one of the cleanest demonstrations of real multi-agent intelligence I’ve seen so far.
Not another “look, two chatbots are talking” demo.
An actual framework for how agents can infer who they’re interacting with and adapt on the fly.
The paper is “Multi-agent cooperation through in-context co-player inference.”
The core idea is deceptively simple:
In multi-agent environments, performance doesn’t just depend on the task.
It depends on who you’re paired with.
Most current systems ignore this.
They optimize against an average opponent.
Or assume fixed partner behavior.
Or hard-code roles.
Google does something smarter.
They let the model infer its co-player’s strategy directly from the interaction history inside the context window.
No retraining, separate belief model and no explicit opponent classifier.
Just in-context inference.
The agent observes a few rounds of behavior. Forms an implicit hypothesis about its partner’s type. Then updates its own strategy accordingly.
This turns static policies into adaptive ones.
The experiments are structured around cooperative and social dilemma games where partner types vary:
Some partners are fully cooperative.
Some are selfish.
Some are stochastic.
Some strategically defect.
Agents without co-player inference treat all partners the same.
Agents with inference adjust.
And the performance gap is significant.
What makes this paper uncomfortable for a lot of current “multi-agent” hype is how clearly it shows what real coordination requires.
First, coordination is not just communication. It’s modeling the incentives and likely actions of others.
Second, robustness matters. An agent that cooperates blindly gets exploited. An agent that defects blindly loses cooperative gains. The system must dynamically balance trust and caution.
Third, adaptation must happen at inference time. In real deployments, you cannot retrain every time the population changes.
The most interesting part is that this capability emerges purely from structured context.
The model isn’t fine-tuned to classify opponent types explicitly. It uses behavioral traces embedded in the prompt to infer latent strategy.
That’s belief modeling through language.
And it scales.
Think about where this matters outside toy games:
Autonomous trading systems reacting to different market participants.
Negotiation agents interacting with unpredictable humans.
Distributed AI workflows coordinating across departments.
Swarm robotics where teammate reliability varies.
In all these settings, static competence is not enough.
Strategic awareness is the bottleneck.
The deeper shift is philosophical.
We’ve been treating LLM agents as isolated optimizers.
This paper moves us toward agents that reason about other agents reasoning about them.
That’s recursive modeling.
And once that loop becomes stable, you no longer have “a chatbot.”
You have a participant in a strategic ecosystem.
The takeaway isn’t that multi-agent AI is solved.
It’s that most current systems aren’t even attempting the hard part.
Real multi-agent intelligence isn’t multiple prompts in parallel.
It’s adaptive belief formation under uncertainty.
And this paper is one of the first clean proofs that large models can do that using nothing but context.
Paper: Multi-agent cooperation through in-context co-player inference
tweet