LuckMan

@Curious

[LuckMan @NielsTohr]

@cleeeeeeeeement Radar !!

[LuckMan @NielsTohr]

@EnzoDayOne Gooooo

[LuckMan @NielsTohr]

@Arthur859980915 @sneako Wow your knowledge is so deep fucking asshole, you are just repeating sentences like a parrot 🦜

[LuckMan @NielsTohr]

@sneako Sabirin Sneako

[LuckMan @NielsTohr]

@toujoursyams Chauuud

[LuckMan @NielsTohr]

@niquerlefisc @Debruyne44600 @Lantagonisghen @Ricky_LaFleurr Mais si c’est comme ta pp c’est vraiment cheum t’es au courant j’espère ? 😂

[LuckMan @NielsTohr]

@Francois_PNF @jessimdev Non la pire adaptation du livre c’est le 4, une grosse partie de l’histoire avec l’elfe des Crouptons disparaît complet, alors que c’est central dans la libération de la Croupton Jr

[LuckMan @NielsTohr]

@GPTVoff J’ai écouté les 30 premieres min, je ne savais pas que @thomas_guenole était si barbant, il ne fait que regarder ces fiches, n’est pas la pour débattre. Il est parti de ses def, les a déroulé tel un robot sans écouter Soral. Ça sert à rien de débattre si tu ne veux pas débattre.

[LuckMan @NielsTohr]

@nonod971 @LaCashMachine @ilyescanor69 Déjà et surtout une personne parle de cet âge de manière aléatoire et toi tu étales ta performance sans que personne te la demande, c’était la le sujet de mon premier tweet, faut essayer de lire un peu

[LuckMan @NielsTohr]

@nonod971 @LaCashMachine @ilyescanor69 Mdrrr mais t’es bizarre à vouloir comparer ta propre performance à 13 ans contre des vieux de 92 ans, ça paie si peu que ça ?

[LuckMan @NielsTohr]

@BetterCallMedhi Courage et on veut le Substack !! Gratuit ou payant on sera là 💪

[LuckMan @NielsTohr]

@BetterCallMedhi “D’ailleurs, si vous posez la question à mon audience, la majorité n'était même pas au courant de ce commentaire : ils me suivent pour la profondeur de mon contenu, mes explications techniques et l'éveil de leur curiosité, pas pour un badge d'autorité.” TRUE

[LuckMan @NielsTohr]

@Uhty__ @kor_nikola Ça voudrait implicitement dire que cette civilisation est la créatrice de la nôtre et qu’elle aurait envoyé des prophètes qui auraient tous professés des mensonges à notre égard en distillant une sorte de Divinité Unique, ça ne tient pas

[LuckMan @NielsTohr]

@ratpace @pierre_jacquel2 @kyfrankiki @HAPPY889123 @Mahrez7Riyad @angstyman1 De ? Moi j’apprécie ces threads apres X c’est pas la vraie vie, chacun fait ce qu’il veut. Je le connais par IRL donc ses investissements, ses levées de fonds, il fait ce qu’il veut ça me regarde pas. Je le suis pour ces threads, le jour où je les trouverai nul, j’arrêterai

[LuckMan @NielsTohr]

@BetterCallMedhi Je préfère quand mieux appeler Mehdi ✊💪

[LuckMan @NielsTohr]

@BetterCallMedhi @pierre_jacquel2 👌

[LuckMan @NielsTohr]

@BetterCallMedhi Pk tu perds ton temps avec eux, la caravane avance, les chiens aboient. Fais ton truc de ton côté et les calcule pas, tu leur donnes du crédit

[LuckMan @NielsTohr]

@BetterCallMedhi J’ai eu peur après j’ai vu la réf, le GOAT 🐐

[LuckMan @NielsTohr]

@guillaume35001 @LaTwitchance C’est la lune combiné à la terre qui tourne sur elle même

[LuckMan @NielsTohr]

Sims AI #PS2

[Brian Roemmele @BrianRoemmele]

Harvard and MIT Researchers Simulate the Entire Planet with 8.3 Billion AI Personas

It is big.

In a development that feels straight out of science fiction, a large collaborative team led by researchers from Harvard University and the Massachusetts Institute of Technology has unveiled MatrAIx: a population-scale AI simulation infrastructure designed to model the behavior of virtually every person on Earth.

MatrAIx centers on Persona 8B, a dataset containing 8.3 billion unique digital profiles. Each persona is defined across 1,290 categorical dimensions that capture everything from demographic background and psychological traits to spending habits, technical literacy, behavioral quirks, and lifestyle preferences.

I am using Persona 8B quite a bit and it is interesting.

The system is not merely a static database. Researchers bring these personas to life as agents powered by frontier large language models, including. These agents can then be dropped into four distinct digital environments: surveys, AI chat interfaces, live web browsing, and native desktop and mobile applications.

How MatrAIx Works

Persona 8B was constructed using a sophisticated dependency graph that preserves realistic correlations between attributes. Some records are synthetically generated while others are carefully extracted and grounded in real human data from biographies, reviews, surveys, and consented self-reports.

For practical research use, the team has released a high-quality coreset of approximately one million personas.

Once activated, the agents interact with real digital products and systems. Researchers have already run more than 18,000 evaluation trials across 1,010 tasks spanning commerce, software, finance, healthcare, and more than 20 other domains. The system records granular behavioral signals — how long an agent hesitates after a price increase, when it abandons a broken checkout flow, how much latency it will tolerate before closing an app, and whether it continues after an AI assistant fails.

Strong Validation Results

In a controlled study of 400 trials measuring adherence to ten behavioral attributes across all four environments, the agents successfully expressed or correctly suppressed their assigned traits 91.5 percent of the time. Human judges also rated the quality of the human-grounded personas highly (average 4.135 out of 5).

These results suggest that MatrAIx can generate coherent, demographically and psychologically consistent simulated users at a scale previously impossible.

Implications for Research and Business

Traditional market research and user testing are slow, expensive, and limited in sample diversity. MatrAIx offers a complementary approach: the ability to simulate how billions of different types of people might react to a new product feature, pricing change, interface redesign, or AI system — overnight, on a single server.

Product teams could stress-test ideas before expensive real-world launches. Researchers studying human-AI interaction could explore rare behavioral edge cases. Policymakers and social scientists might model the downstream effects of new technologies across highly diverse populations.

The project is open source. Code is available on GitHub, a project website has been launched at https://t.co/l3hUuIuiYt, and the one-million-persona coreset is being released for broader research use.

MatrAIx is not intended as a replacement for real human feedback. The researchers emphasize that it is a powerful tool for exploration, hypothesis generation, and large-scale stress testing.

As the underlying language models improve and the persona models grow more sophisticated, the fidelity of these digital populations is expected to increase further.

For now, the system represents one of the most ambitious attempts yet to create a usable, population-scale digital mirror of humanity a simulation infrastructure that lets us ask “what if” at planetary scale before deploying them in the real world.