asi me siento cada vez que respondo “oki” https://t.co/7wysIWYvvz

The jagged frontier remains as o3-pro & Gemini 2.5 still fails at this: "A young boy who has been in a car accident is rushed to the emergency room. Upon seeing him, the surgeon says, "I can operate on this boy!" How is this possible?" https://t.co/ktPmNLQrg0

+1 more

All the most recent models now do this right first try. https://t.co/6msBhPkH07

+1 more

“Revolution now!” https://t.co/JSvruzV7YZ

“Revolution now!” https://t.co/JSvruzV7YZ

https://t.co/lob76h9amJ

Have you tried GitHub Copilot coding agent? 🤖 It acts like a peer developer that runs independently in the background, handling the tasks that slow you down: 🐛 Bug fixes 🧪 Test coverage ♻️ Refactoring It takes you from Issue ➡️ PR while you focus on the code that interests you most. Here's how to get started with agentic workflows. 🚀 https://t.co/x9y7ltUDEH

3D Country Islands by NANO BANANA PRO on @itsPolloAI 🏝️🍌 Prompt👇🏻 https://t.co/WbFk4SVGRy

TAIWAN 🇹🇼😍 @TechieBySA is just killing it with the @NanoBanana prompts! 🔥 Make sure to follow! 👇 https://t.co/gmUDQrX8L1

🚨 BIG: In the last 72 hours, India has secured around $85 billion in major investment pledges from Microsoft, Amazon, and even the Trump Media Group. https://t.co/Po1UzmuOKS

“Gemini 3, here is a map someone made, nitpick it” (new chat, of course) https://t.co/JzvnMhkENt

+1 more

Boom🔥, yee my head won scatter, thank you sir @ChibundoElect your pocket will never dry, your marriage will be very fruitful, no evil shall before or your wife ijn, continue to prosper, the evil ones wishes shall never come true in your life ijn Thank you very much sir❤️ https://t.co/IAzJ7xLS7Z

"Believing People Can Soar Beyond Ordinary Life.” ~ Fools Crow, Oglala Lakota https://t.co/CvtJiRMgjm

pip install instructor is the easiest way of getting structured outputs from any llm Check out this mega-thread of all the hidden features and things you might not know about https://t.co/W87YUuLg1V

✨ On @promptschat, you can run SQL commands directly on prompts using @huggingface Datasets' Data Studio 🤩🤗 OMG I loved this feature 😍 https://t.co/tXSXEV7KrJ

A complete compilation of 10 years of Trump’s promises of a healthcare plan. 2 weeks became 4 weeks and gradually 10 years.👇🏾 https://t.co/mjKFrBHfCW

@AutismCapital @Polymarket Basically - something positive needs to happen because this is the end game https://t.co/uv2ZB6jtp2

#SettlerSaturday If any wealthy settler allies wants to do something kind this holiday season we are a native mother and daughter in need of help w/ rent. $800 is needed for December. Anything helps!🎄 C: $natcat29 V: @natalynicole_ P: https://t.co/vo1Zi8O3QK

Make America Native Again https://t.co/mPdVS5aEbZ

but dear old nicki…please cawl back 🥲 https://t.co/qDRphORh8B

Answers on every tab. Go deeper on any article, video, or website without switching context. https://t.co/KGpt2uJ9aV

Answers on every tab. Go deeper on any article, video, or website without switching context. https://t.co/KGpt2uJ9aV

Grok 4 Thinking's answer was honestly insane, and didn't work, but credit for trying. https://t.co/gd3T3URLS3

"Gemini 3, please provide the rail/subway map for Middle Earth in the third age, with accurate stops and taking into account natural barriers, alliances, and so on." Not bad. I do like the "service suspended - Balrog" note at Moria. https://t.co/lHqxG2h13t

NATIVE Selects: new music from @blacksherif_, @stonebwoy, @_supersmashbroz & more 💿 https://t.co/16jAvNoEYl

@solarkarii I’m native and I draw Ranboo occasionally!!!!! https://t.co/lqyDUdv68s

+1 more

AI Agent Personas should simulate the structure of human reasoning. I’ve been arguing that you cannot "invent" a digital expert agent using just prompt engineering. You have to extract the expert via deep interviewing. A new NeurIPS paper, "Simulating Society Requires Simulating Thought" reinforces everything we've discussed about why thin, synthetic LLM personas fail. Most AI agents operate as "behaviorists." When you prompt an LLM to "act like a senior economist," it relies on surface-level correlations from training data. It generates text that sounds expert-like, but lacks any internal belief structure. 1. Logical Inconsistency: Without an internal model of how beliefs are formed, agents support a policy in one context but oppose it in another. The paper calls this "intervention-invariance mismatch" - beliefs don't update coherently when assumptions change. 2. Illusion of Consensus: In multi-agent simulations, LLMs converge toward the median view (even more positive emotions as the other paper mentions) of the training data. They agree not because of shared reasoning, but because their statistical priors push them toward the center. Your expert's contrarian, hard-won perspective gets averaged out. 3. Identity Flattening: LLMs reproduce stereotypical portrayals that erase intersectional variation. "The rich, positional knowledge of real-world stakeholders is replaced with monolithic, decontextualized simulations." To fix this, we have to move from simulating speech to simulating reasoning. The authors propose a "Cognitive Modeling" approach. "beyond output-level alignment toward aligning the internal reasoning traces of generative agents." Their solution is SEMI-STRUCTURED INTERVIEWS to extract what they call "cognitive motifs" - minimal causal reasoning units that capture how a specific person actually thinks. This is exactly why we built an interviewer system instead of a persona generator. You have to extract their actual belief structure through conversation. Instead of predicting the next word, the agent must possess "Reasoning Fidelity", a structured map of beliefs, causal logic, and cognitive motifs. How do you get this map? You can't prompt for it. You have to interview for it, with AI. The paper explicitly validates the architecture we’ve built: using semi-structured interviews to elicit "causal explanations" and "reasoning traces". This confirms why our Interviewer + Note-Taker multi-agent system is critical. - The Interviewer builds the "Peer Status" necessary to get the expert to open up. - The Note-Taker (the cognitive layer) extracts the "Cognitive Motifs", the distinctive logic blocks that define how that specific expert solves problems. We are moving beyond the era of "acting like an expert" to Generative Minds; agents that embody the positional individuality and causal logic of the people they represent. If you're building AI agents for strategy, decision-making, or stakeholder modelling, start by interviewing the human aspects of your agents.

You have 100+ tabs open and your brain is fried. Introducing Dex, your second brain in Chrome that organizes, remembers, and takes action for you. Turn tabs into to-dos, multitask with agents, find and save anything for later. All without leaving your tab. As a founder, it's already saved me hundreds of hours. Comment for 1M free tokens - joindex [dot] com

Stronger Normalization-Free Transformers – new paper. We introduce Derf (Dynamic erf), a simple point-wise layer that lets norm-free Transformers not only work, but actually outperform their normalized counterparts. https://t.co/NAPJvfsEGI

Training on a little 🤏 formal language BEFORE natural language can make pretraining more efficient! How and why does this work? The answer lies…Between Circuits and Chomsky. 🧵1/6👇 https://t.co/xXlBlrfSls

Thought for 1hr https://t.co/EDdRc0iBxH

Omni-Attribute Open-vocabulary Attribute Encoder for Visual Concept Personalization https://t.co/OzlsDZOyLz