Here are some links to some of my current projects:
GuestbookSmall-scale manual LLM performance comparison benchmark
Can you get the bot to respond properly?
Pre-prompted Chatbot characters
AI models playing chess
(using your own API keys)
Long-Chain-of-Thought Reasoning Models and how "Thinking" affects token usage
(warning: bugs!)
Using minimalistic raw PGN movetext continuation
Single-elimination chess tournament between 15 AI models
Respond to an LM Arena armchair critic
grieving friend
washing hands without arms
Concede or continue token waste? (DeepSeek-R1 & Sonnet 3.7 Thinking)
orienting a nail
robbing, location, guard
robbing the gas station
Creating a simple AI benchmarking website template, how meta
Creating a Steins;Gate themed terminal page
a discord request
(warning: bugs!)
(warning: bugs!)