~/bookmarks

How to improve the output quality for creative writing with Kimi K2

lower the temperature. default on the Kimi website is very high, around 1.

LLM Memory

Some thoughts on implementations

GLM 4.5-Air-106B and Qwen3-235B on AMD “Strix Halo” AI Ryzen MAX+ 395 (HP Z2 G1a Mini Workstation)

In this video, I show how to run large language models like Qwen3-235B in Q3_K_XL and GLM 4.5-Air-106B in Q6_K_XL on any AMD Ryzen AI MAX “Strix Halo”...

ComposerAI

AI email client / mailbox for agentic search and tasks

Java Chat

RAG-powered Java learning chat app with streaming answers and citations

Researchly

AI-powered web search with a contextual chat assistant

AI Agents in Action

Micheal Lanham

AI Agents in Action covers the development of production-ready assistants, multi-agent systems, and behavioral agents. The text details the core compo...

The RLHF Book

Nathan Lambert

This is a guide to reinforcement learning from human feedback (RLHF), alignment, and post-training for Large Language Models (LLMs). Author Nathan Lam...

User Interviews

Platform connecting companies with participants for user research and customer feedback studies.

WeLoveNoCode

Platform connecting businesses with no-code developers and tools.

Switch

Switch provides a simple way to pool money and spend with a group.