🤖 RL

Reinforcement learning, RL, robotics, mjx, mujoco, mels

AI Plays Risk – Lessons from a silly benchmark
andreasthinks.me·7h·
Discuss: Hacker News
💬AI
Backpropagating through a maze with candle and WASM
yberreby.com·17h·
Discuss: Hacker News
💬AI
Car Reinforcement Learning Training
github.com·3h·
Discuss: Hacker News
💬AI
Good context leads to good code: How we built an AI-Native Eng Culture
blog.stockapp.com·3h·
Discuss: Hacker News
💬AI
DSPy Simba Explained
blog.mariusvach.com·23h·
Discuss: Hacker News
💬AI
LLMs Can't Navigate Through the Physical World
hansenq.substack.com·53m·
Discuss: Substack
💬AI
The Model Is the Product
pleias.fr·8h·
Discuss: Hacker News
🌿SCM
How to train your robot: Wear a tiny one in a baby carrier
theregister.com·1d·
Discuss: Hacker News
💬AI
Show HN: Principles of Building AI Agents book [pdf]
github.com·7h·
Discuss: Hacker News
💬AI
Guided Learning in Gemini: From answers to understanding
blog.google·5h·
Discuss: Hacker News
💬AI
Teach Me to Think Like an Operator
5iprojects.com·1h·
Discuss: Hacker News
💬AI
Ten Thousand Agents
notes.npilk.com·4h·
Discuss: Hacker News
💬AI
Simulated Society of 10k AI Agents
theunwindai.com·2d·
Discuss: Hacker News
💬AI
Software Development with AI – Perspective from an experienced software engineer
nootn.com.au·9h·
Discuss: Hacker News
🌿SCM
We're Building the Future of the Startup Economy with AI
angellist.com·4h·
Discuss: Hacker News
💬AI
Towards Automating Scientific R&D
ghofrani.net·1d·
Discuss: Hacker News
🌿SCM
When the bubble bursts – AI in music production
musicradar.com·4h·
Discuss: Hacker News
💬AI
We beat GPT-4o's baseline with a simple re-prompting loop
aimon.ai·22h·
Discuss: Hacker News
💬AI
How to build the #1 open source terminal-use agent
letta.com·1d·
Discuss: Hacker News
💬AI
How to build realistic AI companions
emotionmachine.ai·20h·
Discuss: Hacker News
💬AI