How does Agentic AI work? Collects data (APIs, sensors, logs, queries) Reasons & plans with memory + context Executes actions, learns from feedback Produces autonomous, adaptive responses AI that doesn’t just respond — it acts.
#AgenticAI #AI #Automation
MACHINE LEARNING
-
How Agentic AI Works: From Data Collection to Autonomous Action
By
–
-
EGGROLL: Gradient-Free LLM Training Achieves 100x Throughput
By
–
Could evolution replace gradients for LLM training? Introducing EGGROLL, a new paper that makes gradient-free training actually practical 100x training throughput vs vanilla ES 100x memory reduction 91% inference speed
Pure integer training Trending #1 on alphaXiv -
Gemini 3 Secret: Pre-training and Post-training Improvements
By
–
Actually if you want to know what the real ‘secret’ is 😀 it’s world-class research AND world-class engineering AND world-class infra all working closely together with relentless focus and intensity… Oriol Vinyals (@OriolVinyalsML) The secret behind Gemini 3? Simple: Improving pre-training & post-training 🤯 Pre-training: Contra the popular belief that scaling is over—which we discussed in our NeurIPS '25 talk with @ilyasut and @quocleix—the team delivered a drastic jump. The delta between 2.5 and 3.0 is as big as we've ever seen. No walls in sight! Post-training: Still a total greenfield. There's lots of room for algorithmic progress and improvement, and 3.0 hasn't been an exception, thanks to our stellar team. Congratulations to the whole team 💙💙💙 — https://nitter.net/OriolVinyalsML/status/1990854455802343680#m
→ View original post on X — @oriolvinyalsml, 2025-11-22 20:32 UTC
-
Les sept sommets de l’intelligence artificielle : évolution et stratégie
By
–
Scaling Ascent Peak: The Seven Summits of Artificial Intelligence In my latest article, I chart the evolution of AI—from the early days of symbolic logic to today’s autonomous agents, and what lies beyond. This journey is more than a history lesson: it’s a strategic framework
-
Visualizing how Reinforcement Learning works
By
–
This is how Reinforcement Learning works, visualized https://t.co/RZAcQZ2vbc
— God of Prompt (@godofprompt) 22 novembre 2025This is how Reinforcement Learning works, visualized
-
Windsurf’s AI Pair Programming Mode
By
–
Windsurf got a new mode where Claude Sonnet 4.5 would do all the planning and faster SWE-1.5 model will be applying changes to the code. AI pair programming
-
Recommends paper as great intro to tabular foundation models
By
–
Really recommend their paper, it's a great intro to tabular foundation models:
-
TabPFN-v2 could replace XGBoost and Random Forest
By
–
Anyone heard of TabPFN-v2?
Soon the end for XGBoost and Random Forest -
Resolving Ambiguous Prompts Across Technical Domains
By
–
7. Ambiguity Resolution Under Pressure
— God of Prompt (@godofprompt) 22 novembre 2025
Prompt:
Interpret the vague instruction “Prepare the model for tomorrow’s run” in 10 completely different ways across these domains: machine learning, finance, biotech, aerospace, logistics, cybersecurity, robotics, meteorology, energy… pic.twitter.com/6WWQeMShK47. Ambiguity Resolution Under Pressure Prompt: Interpret the vague instruction “Prepare the model for tomorrow’s run” in 10 completely different ways across these domains: machine learning, finance, biotech, aerospace, logistics, cybersecurity, robotics, meteorology, energy
-
Mathematical Generalization Stress Test Prompt for AI Models
By
–
4. Mathematical Generalization Stress Test
— God of Prompt (@godofprompt) 22 novembre 2025
Prompt:
Generalize the formula for expected error in a Monte Carlo model when sampling distribution skewness increases non-linearly. Create three versions: a practical heuristic for engineers, a fully rigorous derivation for… pic.twitter.com/RbcqMdnoam4. Mathematical Generalization Stress Test Prompt: Generalize the formula for expected error in a Monte Carlo model when sampling distribution skewness increases non-linearly. Create three versions: a practical heuristic for engineers, a fully rigorous derivation for