RSS.Social

hlfshell

follow: @[email protected]

Posts

A Proposal for Research

Multi-Turn Credit Assignment with LLM Agents

DeepSeek V3 + GRM SPCT: Self-Improving AI Reward Models

The Physical Turing Test: Nvidia's Vision for Embodied AI

Clever tooling for a 3d printed arm

Mechanical Movement References

DeepSeek GRM and SPCT - Complex Domain Rewards

Moldable Design

go-arkaine-parser

eli5-equations

hiredcoach

reflecta

SDx Replit Hackathon

Resistance with Data Preservation

Cursor + Other AI Tools

DeepSeek + Inference-Time Scaling and Generalist Reward Modeling

Interview Practice App

arkaine 0.0.21; next steps

Just give me a second to think...

arkaine 0.0.20 - TTS

arkaine docs

BitNet b1.58 Reloaded

Mathematica

GRPO in DeepSeek-R1

Liquid Time Constant Neural Networks

DeepSeek R1

eli5-equations

Mini hack-a-thon

Increased creativity by thinking longer

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

I'm afraid I can't do that, Dave...

(Rapidly) introducing arkaine

Diffusion Models Are Real-Time Game Engines

Google DeepMind's Grandmaster-Level Chess Without Search

Representation Engineering and Control Vectors - Neuroscience for LLMs

Nerd Sniped - Solving for Jumbles and Letter Boxed

Utilizing LLMs as a Task Planning Agent for Robotics

A Corollary to Conway's Law - Build for The Team You Have

Repeatable Dev Environments for ROS2

State of the art in LLMs + Robotics - 2023

Reinforcement Learning with a Pick and Place Robotic Arm

Ultralearning

Evolving a Neural Network Traffic Controller

Golang Docker Harness

Evolutionary Neural Networks

Projects

Talks

Books