maxim-saplin

Engine Elo ratings: Player Games Elo ±95%CI

random 4000 -122.3 23.0 stockfish-lvl-1 1000 824.9 64.2

Stage 2: LLM Elo Ratings Player Games Elo ±95%CI

3x-o4-mini-2025-04-16-low_41mini-t03 33 114.6 133.1

maxim-saplin

1. Connect to DLC-02 via Mean Well windows app (either using USB ot Ethernet)
2. Scan DALI lamps, assign lamps to virtual lamps

• 2.1. If you have lamps that change color you need to 1st define the type of virtual lamp and only than assign/drag the actual DALI lamp
• 2.2. Each virtual lamp gets an address, e.g. A0 means bus A lamp 0 - use this for addressing

3. You can test is lamp works via commands line (assuming A0 address, also use correct IP and port which by default is 502)

• On mbpoll -0 -m tcp -p 502 -a 255 -t 4:hex -r 41001 192.168.31.27 0x0100 0x0101 0x0000 0x0000
• Off mbpoll -0 -m tcp -p 502 -a 255 -t 4:hex -r 41001 192.168.31.27 0x0100 0x0100 0x0000 0x0000

4. In HA you might want to install 'File Editor' to change configs

maxim-saplin

Install on WSL2

1. Installed Ubuntu-24.04 from the Mircosot Store -> Types WSL and Selected the most recent Ubuntu

2. Windows Terminal -> wsl -d Ubuntu-24.04 (using -d to specify distro name, I have multiple distros)

3. Installing SGLang

Copying and pasting from docs (https://docs.sglang.ai/start/install.html) didn't quite work.

maxim-saplin

Proxy (to Player_Black):

You are a professional chess player and you play as black. Now is your turn to make a move. Before making a move you can pick one of the following actions:
- 'get_current_board' to get the schema and current status of the board
- 'get_legal_moves' to get a UCI formatted list of available moves
- 'make_move <UCI formatted move>' when you are ready to complete your turn (e.g., 'make_move e2e4')

--------------------------------------------------------------------------------
Player_Black (to Proxy):

maxim-saplin

Proxy (to Random_Player):

You are a random chess player.

--------------------------------------------------------------------------------
Random_Player (to Proxy):

get_legal_moves

--------------------------------------------------------------------------------

maxim-saplin

You are an AI assistant designed to provide detailed, step-by-step responses. Your outputs should follow this structure:

1. Begin with a <thinking> section.
2. Inside the thinking section:
   a. Briefly analyze the question and outline your approach.
   b. Present a clear plan of steps to solve the problem.
   c. Use a "Chain of Thought" reasoning process if necessary, breaking down your thought process into numbered steps.
3. Include a <reflection> section for each idea where you:
   a. Review your reasoning.
   b. Check for potential errors or oversights.

maxim-saplin

# pip install -U git+https://github.com/huggingface/transformers.git

from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
import torch
import time


def chat_with_ai(model, tokenizer):
    """
    Function to simulate chatting with the AI model via the command line.

maxim-saplin

def is_special_number(number):
    if number == 7:
        return True
    elif number == 18:
        return True
    else:
        return False

def is_special_number_2 (number):
    return number in [7, 18]

maxim-saplin

// sealed classes are abstract (can't be instatiated) and can only be
// implemented in the same library (library in Dart is one file be default)
sealed class Message {
}

class TextMessage implements Message {
  final String content;
  TextMessage(this.content);
}

maxim-saplin

# https://matplotlib.org/matplotblog/posts/animated-fractals/
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.animation as animation
import time

x_start, y_start = -2, -2  # an interesting region starts here
width, height = 4, 4  # for 4 units up and right
density_per_unit = 80  # how many pixles per unit