Nous Research · pinion

Nous Research@NousResearch

Introducing the Manim skill for Hermes Agent. Manim is an engine for creating precise programmatic animations for mathematical and technical explainers, made famous by the @3blue1brown channel.

related

▶@NousResearch

▶@coreyhainesco design engineering is not animations https://micro.bossadizenith.me/writing/animations@bossadizenith 🔖 Bookmark this post to start building with the updated Gemini Live model.@googleaidevs

@ctatedev Best Model Per Use-Case Presentations - Gemini 2.5 Full-stack apps - GPT-5 Codex, Sonnet 4.5 Docs - Gemini 2.5, GPT-5 thinking Videos - Sora 2 Images - Nano Banana Coding - Sonnet 4.5, Grok Code Fast Browser use - Sonnet 4.5 Doc Processing - Gemini Flash Enterprise Search - Sonnet 4.5 Data analysis (complex) - Opus 4.1 Agentic workflows - Sonnet 4.5, Haiku 4.5@bindureddy Introducing eve, an agent framework. 𝚊𝚐𝚎𝚗𝚝/ 𝚊𝚐𝚎𝚗𝚝.𝚝𝚜 𝚒𝚗𝚜𝚝𝚛𝚞𝚌𝚝𝚒𝚘𝚗𝚜.𝚖𝚍 𝚝𝚘𝚘𝚕𝚜/ 𝚜𝚔𝚒𝚕𝚕𝚜/ 𝚜𝚊𝚗𝚍𝚋𝚘𝚡/ 𝚜𝚌𝚑𝚎𝚍𝚞𝚕𝚎𝚜/ Like Next.js, for agents. https://vercel.com/blog/introducing-eve@vercel

▶@emilkowalski≡ 2

▶@hyperbrowser

@techNmak I've tried all ( 74 😵‍💫 ) AI Coding Agents & IDEs [Rork, CodeRabbit, Anima, Zed, Factory, Cursor, Windsurf, Copilot, Lovable, Bolt, v0, Replit, MarsX, Canva, Devin, Github Spark, Vercel, Lindy, Warp, Figma, Cline, Vibe Coder & more] The most complete list ever made (with demos & notes):@johnrushx

@OpenRouter≡ 10+2

@LiorOnAI Top 5 local LLMs: 1. GLM-4.5-air: best agentic/coding model that runs on consumer hardware at very decent speeds. Rivals Claude 4-sonnet. 2. Nousresearch/hermes-70B: the only model that will do whatever you ask, and tell you whatever you want to know. Literally critical to have. 3. GPT-OSS-120B: very intelligent it’s like having 4o at home, great context window, great agent 4. Qwen3-coder-30B-3A-instruct: very good coding agent, excellent workhorse, incredibly fast 5. Mistral-magistral-small: very fast, excellent agent, great coder, multimodal, punches way, way, above its size. I would be okay never using a proprietary llm, although given the subsidised compute I will continue to use them since I’m getting free leverage.@0xSero

@emilkowalski I took the @karpathy autoresearch loop and pointed it at markets. 25 AI agents debate macro, rates, commodities, sectors, and single stocks daily. Every recommendation scored against real outcomes. Worst agent by rolling Sharpe gets its prompt rewritten by the system. Keep or revert. Same loop, prompts are the weights, Sharpe is the loss function. Trained the agents on 18 months of market data. 378 iterations. 54 prompt modifications, 16 survived. The system learned which agents to trust using Darwinian weights — geopolitical, commodities, and the @BillAckman quality compounder rose to the top. The agents even figured out their own portfolio manager was the weakest link before we did! Deployed the trained agents. +22% in 173 days. Best pick: AVGO at $152, held for +128%. The final prompts are evolutionary products — shaped by market feedback, not human intuition. Now running live with my own capital. https://github.com/chrisworsey55/atlas-gic Part hedge fund, part research experiment :)@Chris_Worsey

▶@ElijahKurien After a couple hours of work, I finally finished developing my first ever skill. :D Claude’s frontend skill tells the AI to "pick an extreme aesthetic" and "be creative." The problem tho is LLMs are just based on probability. Without strict rules, they statistically default to the most likely patterns, that's where AI slop comes from. To get clean and production-grade UI, you need to override these biases with some engineering constraints. I open-sourced Taste-Skill to fix this. :) Check it out! https://github.com/Leonxlnx/taste-skill (still early lots of improvements are on the way)@LexnLin

@Zai_org Introducing Vibe SDK@rauchg