1/6 Long-horizon agentic tasks are breaking our mental models. More tokens, bigger models, and best-of-N only go so far. Orchestrated approach to test-time-compute scaling is what long-horizon tasks need. Here’s what we learned using SWE-bench as a test case. Read the blog for
LLMS
-

Generative AI Tech Stack: Six Layers Powering Autonomous Agents
By
–
The Generative AI ecosystem is evolving into a full tech stack — powering autonomous AI agents.
From infrastructure and LLMs to RAG pipelines, agent behaviors and orchestration layers, this framework shows the 6 layers driving next-gen AI systems. Credit: @goyalshalini #AI -
Hinton: AI Can Tackle Math Autonomously as a Closed System
By
–
Le père de l'IA, Geoffrey Hinton, affirme que les mathématiques sont un système fermé, ce qui permet aux IA de les aborder comme un jeu.
— VISION IA (@vision_ia) 7 janvier 2026
Elles peuvent se poser leurs propres problèmes, tester des démonstrations et apprendre de ce qui fonctionne, sans dépendre d’exemples humains.… pic.twitter.com/TCciauPV22Le père de l'IA, Geoffrey Hinton, affirme que les mathématiques sont un système fermé, ce qui permet aux IA de les aborder comme un jeu. Elles peuvent se poser leurs propres problèmes, tester des démonstrations et apprendre de ce qui fonctionne, sans dépendre d’exemples humains.
-

Cursor reduces tokens by 46.9% with dynamic context
By
–

Cursor release a dynamic context discovery for all models which reduced total tokens by 46.9%
-

Native Parallel Reasoner: LLMs Learn Multi-Path Problem Solving
By
–
What if an AI could truly think in parallel, not just fake it? Researchers at BIGAI introduce Native Parallel Reasoner (NPR), a new framework that teaches LLMs to break down and solve problems across multiple "thought" paths simultaneously, learning by trial and error. The
-

Gemini hits 20% AI chatbot traffic share
By
–


Gemini surpassed 20% traffic share threshold among the overall traffic for AI chatbots. Grok is above 3% now as well
-
ChatLLM: Intelligent Model Routing for Seamless Workflows
By
–
We built ChatLLM by Abacus AI so you don’t have to think about models.
— Abacus.AI (@abacusai) 7 janvier 2026
You just type what you want to do.
It routes to the model that fits – reasoning, speed, creativity, longer workflows.
Keeps your flow going.
What would you use this for? pic.twitter.com/WjkBe7LBUtWe built ChatLLM by Abacus AI so you don’t have to think about models. You just type what you want to do.
It routes to the model that fits – reasoning, speed, creativity, longer workflows. Keeps your flow going. What would you use this for? -

LFM2.5: Next Generation On-Device AI from Liquid AI
By
–
Introducing LFM2.5: The Next Generation of On-Device AI | Liquid AI https://
buff.ly/6x7JmPE
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Three.js and Major Libraries Adopt llms.txt Standard
By
–
Great to see @threejs supporting llms.txt. I have noticed that the majority of libs/services I work with nowadays seem to have an llms.txt nowadays. Makes me happy! (I've been really enjoying the very comprehensive @GeminiApp llms.txt recently for writing Gemini code.)