Stories by simonpure

Multi-agent cooperation through in-context co-player inference

Puzzle Challenge

AutoHarness: Improving LLM agents by automatically synthesizing a code harness

10 years of AlphaGo: The turning point for AI [video]

Autoresearch: Agents researching on single-GPU nanochat training automatically

Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory

Dcsctp: An SCTP Implementation for WebRTC Data Channels in Rust

NousResearch/hermes-agent: The agent that grows with you

Agent-experience: visual reference to patterns, surfaces, and infrastructure

WebKit for SwiftUI [video]

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled

Improving Chain-of-Thought Monitorability Through Information Theory

Inference Engineering

Telos is an open-sourced framework for creating Deep Context

State of Clojure 2025 Results

LongCLI-Bench: Benchmark and Study for Long-Horizon Agentic Programming in CLIs

Design-memory: Extract and reproduce design systems from any website

Will I Be Paid in Tokens?

How Personal AI Agents and Agent Orchestrators Like OpenClaw or GasTown Are Made

Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook

1 2 3 4 5 6 7 8 9 10