Ergin Akin·10h agoMistaking Your Own Ceiling for the Sky: What a Kaggle Simulation and Rust Taught Me About LimitsEngineers and AI practitioners often fall into a quiet, familiar trap: when we cannot solve a problem with the tools in our hands, we…A response icon1A response icon1
Ykassa·19h agoReinforcement Learning (basics)In this article i’ll try to cover some of the basic theoretical concepts in reinforcement learning. Everything else that follows depends on…
Sridatt More·1d agoMy Tiny Model Knew the Way. It just Wouldn’t Say it.Part 2 of teaching a 1.5B reasoning model the Wikipedia game: a bug that hid 9 points, three RL runs that went nowhere, and the side task…A response icon2A response icon2
Ejiabor Chinweogo Rita·2d agoMy Agent is Officially Biting More Than It Can ChewOn this episode of Learning on the Job…
Aneri·2d agoDodge! Teaching a Satellite to Avoid CollisionsImagine you are the controller of a satellite, and a piece of debris is on course to pass within a few kilometers of it. You have a limited…
Bijit Ghosh·3d agoContinuous Learning Loop for Agent MemoryShared memory layer for carrying verified experience across models, harnesses, skills, and codebases.
Ejiabor Chinweogo Rita·3d agoCan My Agent Actually Play Minesweeper ?On this episode of Learning on the Job…A response icon1A response icon1
InGuideWitbyGuideWit·3d agoA warehouse robot can lose a delivery by taking the fastest first stepA robot reaches a junction with a parcel onboard. One route pays a small simulated reward immediately for handing it to a local buffer. The…
Muhammad Hanzala·4d agoI Ran the Full RLHF Pipeline on a Free GPU, Then Pitted PPO Against DPOEveryone talks about RLHF, but few people actually run all of it. I wanted to see every stage with my own eyes, so I built the whole…
Mrutyunjay Patil·4d agoTeaching a model the way you’d teach a kidThe language model behind every chatbot you use, ChatGPT and Claude included, learned the way a kid learns words. It guessed, someone told…