Himalaya Dua

"A new study reveals that young children learn letters and word structures more effectively through handwriting than typing. Researchers taught 5- to 6-year-olds unfamiliar letters and pseudowords using either manual writing or keyboards. Those who practiced by hand performed significantly better on tests of recognition, writing, and pronunciation, especially with unfamiliar word sequences. The study highlights the importance of graphomotor movements in developing reading and writing skills and suggests handwriting should remain central in early literacy education. Key Facts: - Handwriting Advantage: Children who practiced manually learned letters and pseudowords better than those using keyboards. - Motor Skills Matter: Graphomotor movements help imprint letter shapes and word structures into memory. - Free Writing Boost: Among handwriting groups, free copying (without guides) led to the strongest learning outcomes."

The Sparks paper was an innovative attempt at trying to figure out ways of pointing at GPT-4 & saying “there is something unexpected here that is hard to measure right now” I think Early Science Acceleration feels similar. A blurry picture that will become clearer coming years

🏆 Congratulations to OpenMedicine on winning 3rd Prize at the 2025 Scoop AI Hackathon! Built by @ethanyangmd, @Pr_nav_, and @AIBigDataGuy, OpenMedicine is an AI-powered virtual care platform that turns “something’s wrong” moments into fast, evidence-based medical support. By generating structured, clinician-ready notes and guideline-linked recommendations, the system reduces friction for both patients and providers. A thoughtful application of agentic AI in healthcare, made possible with support from @SpoonOS_ai. Well done to the team on building something with real-world impact. 🚀

This is an excellent book. @karpathy said: "Context engineering is the delicate art and science of filling the context window with just the right information for the next step." This book will help you stop thinking about "prompt engineering" and start focusing on "context engineering" instead. This is the book I'd recommend to anyone looking to become an "AI Solutions Architect". Amazon link: amzn.to/3LOo5KU

This Stanford University paper just broke my brain. They just built an AI agent framework that evolves from zero data no human labels, no curated tasks, no demonstrations and it somehow gets better than every existing self-play method. It’s called Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning And it’s insane what they pulled off. Every “self-improving” agent you’ve seen so far has the same fatal flaw: they can only generate tasks slightly harder than what they already know. So they plateau. Immediately. Agent0 breaks that ceiling. Here’s the twist: They spawn two agents from the same base LLM and make them compete. • Curriculum Agent - generates harder and harder tasks • Executor Agent - tries to solve them using reasoning + tools Whenever the executor gets better, the curriculum agent is forced to raise the difficulty. Whenever the tasks get harder, the executor is forced to evolve. This creates a closed-loop, self-reinforcing curriculum spiral and it all happens from scratch, no data, no humans, nothing. Just two agents pushing each other into higher intelligence. And then they add the cheat code: A full Python tool interpreter inside the loop. The executor learns to reason through problems with code. The curriculum agent learns to create tasks that require tool use. So both agents keep escalating. The results? → +18% gain in math reasoning → +24% gain in general reasoning → Beats R-Zero, SPIRAL, Absolute Zero, even frameworks using external proprietary APIs → All from zero data, just self-evolving cycles They even show the difficulty curve rising across iterations: tasks start as basic geometry and end at constraint satisfaction, combinatorics, logic puzzles, and multi-step tool-reliant problems. This is the closest thing we’ve seen to autonomous cognitive growth in LLMs. Agent0 isn’t just “better RL.” It’s a blueprint for agents that bootstrap their own intelligence. The agent era just got unlocked.

@Ai_Vaidehi ML

Releasing a new "Agentic Reviewer" for research papers. I started coding this as a weekend project, and @jyx_su made it much better. I was inspired by a student who had a paper rejected 6 times over 3 years. Their feedback loop -- waiting ~6 months for feedback each time -- was painfully slow. We wanted to see if an agentic workflow can help researchers iterate faster. When we trained the system on ICLR 2025 reviews and measured Spearman correlation (higher is better) on the test set: - Correlation between two human reviewers: 0.41 - Correlation between AI and a human reviewer: 0.42 This suggests agentic reviewing is approaching human-level performance. The agent grounds its feedback by searching arXiv, so it works best in fields like AI where research is freely published there. It’s an experimental tool, but I hope it helps you with your research. Check it out here: paperreview.ai

Day 1 at #TEDAISF2025 connected art, language, science, and space. Tomorrow, Day 2 continues the momentum with panels that spark new ideas, deeper dives, and more to inspire. ⚡ See you tomorrow!