Meta’s SPICE framework pushes AI toward self-learning without human supervision

The new reinforcement learning system lets large language models challenge and improve themselves using real-world data ...

Meta’s SPICE framework lets AI systems teach themselves to reason

The self-play framework uses a 'Challenger' and a 'Reasoner' to create a self-improving loop, pushing the boundaries of AI ...
Nature

Artificial Intelligence in Game Development and Reinforcement Learning

The role of artificial intelligence in game development has expanded significantly over the past decade, merging sophisticated reinforcement learning techniques with innovative game design to create ...
Forbes

The Autonomous Advantage: Reinforcement Learning’s Role In The Next Era Of AI

Expertise from Forbes Councils members, operated under license. Opinions expressed are those of the author. The age of truly autonomous artificial intelligence, where systems proactively learn, adapt ...
VentureBeat

You can now fine-tune your enterprise’s own version of OpenAI’s o4-mini reasoning model with reinforcement learning

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now OpenAI today announced on its ...
TechCrunch

The reinforcement gap — or why some AI skills improve faster than others

AI coding tools are getting better fast. If you don’t work in code, it can be hard to notice how much things are changing, but GPT-5 and Gemini 2.5 have made a whole new set of developer tricks ...
MIT Technology Review

Why we should thank pigeons for our AI breakthroughs

The bird has never gotten much credit for being intelligent. But the reinforcement learning powering the world’s most advanced AI systems is far more pigeon than human. In 1943, while the world’s ...
Wired

This AI Model Never Stops Learning

Modern large language models (LLMs) might write beautiful sonnets and elegant code, but they lack even a rudimentary ability to learn from experience. Researchers at Massachusetts Institute of ...
Computer Weekly

Latest Alibaba AI model demos AI improvements

Just two months after the tech world was upended by the DeepSeek-R1 AI model, Alibaba Cloud has introduced QwQ-32B, an open source large language model (LLM). The Chinese cloud giant describes the new ...
Nature

Secrets of DeepSeek AI model revealed in landmark paper

First peer-reviewed study shows how a Chinese start-up firm made the market-shaking LLM for US$300,000. R1 is designed to excel at ‘reasoning’ tasks such as mathematics and coding, and is a cheaper ...
Wired

Databricks Has a Trick That Lets AI Models Improve Themselves

Using several recent innovations, the company Databricks will let customers boost the IQ of their AI models even if they don’t have squeaky clean data. Databricks, a company that helps big businesses ...