Skip to content

Instantly share code, notes, and snippets.

View MaxWolf-01's full-sized avatar
:electron:

Maximilian Wolf MaxWolf-01

:electron:
View GitHub Profile
@willccbb
willccbb / read_paper.py
Last active August 28, 2025 01:53
Arxiv link to Markdown via Mistral OCR (h/t @simonw)
# /// script
# requires-python = ">=3.12"
# dependencies = [
# "click",
# "mistralai",
# "markdown",
# "requests",
# "beautifulsoup4",
# ]
# ///
@VictorTaelin
VictorTaelin / ic.hs
Last active July 22, 2025 17:55
Minimal Interaction Calculus implementation in Haskell
import Control.Monad (when)
import Data.Char (chr, ord)
import Data.IORef
import Data.Word
import Debug.Trace
import System.IO.Unsafe (unsafePerformIO)
import Text.Parsec hiding (State)
import qualified Data.IntMap.Strict as IntMap
import qualified Data.Map as Map
import qualified Text.Parsec as Parsec
@willccbb
willccbb / REPORT.md
Created March 9, 2025 18:30
Claude Deep Research: ARC-AGI
@VictorTaelin
VictorTaelin / scaling_hvm_optimal_theorem_prover.md
Last active June 25, 2025 01:57
Scalign HVM towards an Optimal Theorem Prover

Scaling HVM towards an Optimal Theorem Prover

Why an Optimal Theorem Prover implies AGI?

Theorem Proving is the ability to solve a mathematical problem. A computer program capable of competently doing that would immediatelly unlock the automation of every intellectual task that a human can perform, because all problems can be reduced to that of solving abstract equations. From the discovery of new physics, to recursive self-improvement and unfathomable

@VictorTaelin
VictorTaelin / materials.md
Last active February 15, 2025 18:15
materials

Company:

Theory:

@VictorTaelin
VictorTaelin / dps_sup_nodes.md
Last active June 28, 2025 09:16
Accelerating Discrete Program Search with SUP Nodes

Fast Discrete Program Search 2

I am investigating how to use Bend (a parallel language) to accelerate Symbolic AI; in special, Discrete Program Search. Basically, think of it as an alternative to LLMs, GPTs, NNs, that is also capable of generating code, but by entirely different means. This kind of approach was never scaled with mass compute before - it wasn't possible! - but Bend changes this. So, my idea was to do it, and see where it goes.

Now, while I was implementing some candidate algorithms on Bend, I realized that, rather than mass parallelism, I could use an entirely different mechanism to speed things up: SUP Nodes. Basically, it is a feature that Bend inherited from its underlying model ("Interaction Combinators") that, in simple terms, allows us to combine multiple functions into a single superposed one, and apply them all to an argument "at the same time". In short, it allows us to call N functions at a fraction of the expected cost. Or, in simple terms: why parallelize when we can share?

A

@VictorTaelin
VictorTaelin / a_b_challenge.md
Last active July 12, 2025 18:47
A::B Prompting Challenge: $10k to prove me wrong!

CHALLENGE

Develop an AI prompt that solves random 12-token instances of the A::B problem (defined here), with 90%+ success rate.

RULES

1. The AI will be given a <problem/> to solve.

We'll use your prompt as the SYSTEM PROMPT, and a specific instance of problem as the PROMPT, inside XML tags. Example:

A::B is a system with 4 tokens: `A#`, `#A`, `B#` and `#B`.
An A::B program is a sequence of tokens. Example:
B# A# #B #A B#
To *compute* a program, we must rewrite neighbor tokens, using the rules:
A# #A ... becomes ... nothing
A# #B ... becomes ... #B A#
@kapad
kapad / toggle-nightlight.sh
Created July 3, 2018 20:30
Script to toggle the Gnome nightlight setting.
#!/bin/bash
setting=$(gsettings get org.gnome.settings-daemon.plugins.color night-light-enabled)
if [[ $setting == "true" ]]; then
gsettings set org.gnome.settings-daemon.plugins.color night-light-enabled false
else
gsettings set org.gnome.settings-daemon.plugins.color night-light-enabled true
fi
@karpathy
karpathy / nes.py
Last active June 7, 2025 14:26
Natural Evolution Strategies (NES) toy example that optimizes a quadratic function
"""
A bare bones examples of optimizing a black-box function (f) using
Natural Evolution Strategies (NES), where the parameter distribution is a
gaussian of fixed standard deviation.
"""
import numpy as np
np.random.seed(0)
# the function we want to optimize