Skip to content

Instantly share code, notes, and snippets.

View p3nGu1nZz's full-sized avatar
🌎
w o r k i n g • f r o m • s p a c e

p3ngu1nZz p3nGu1nZz

🌎
w o r k i n g • f r o m • s p a c e
86 followers · 100 following
View GitHub Profile
@p3nGu1nZz
p3nGu1nZz / gpt5.2-meta
Created December 19, 2025 11:07
A “non-physical, mathematical, hyper-dimensional space” that *contains* all information is a coherent idea in a few different senses—but those senses often get blended together in a way that makes the claim sound more scientifically settled than it is. The most useful way to think about it is to separate (1) **mathematical frameworks that model phenomena**, (2) **philosophical positions about what is ultimately real**, and (3) **spiritual/metaphysical doctrines** that make additional ontological claims.
## 1) The idea is mathematically natural, but “contains all knowledge” is an extra step
It’s completely standard in math/physics to represent a system as a point in a high‑dimensional space:
- **State spaces** in dynamical systems: the “space” is a bookkeeping device for all degrees of freedom.
- **Hilbert space** in quantum theory: a mathematically precise space of possible states.
- **Information geometry** / statistical manifolds: spaces whose points are probability distributions.
- **Markov chains**: evo
@p3nGu1nZz
p3nGu1nZz / gist:ada1d467e74d5505780e46937a867236
Created October 1, 2025 01:13
Fantastic work, Claude! Love what we came up with—that’s exactly what people want. Let’s start by updating #file:ACTION_PLAN.md and deleting #file:M3_COMPLETION_TODO.md. Once that’s done, create a new file in the project root called TODO.md with an unordered [ ] to-do list containing short descriptions for each item (no nesting). Update the instructions in #file:copilot-instructions.md and #file:AGENTS.md to reflect this process. After updating the documentation, commit the changes to the current branch, push them, and then begin working on the tasks in TODO.md.
@p3nGu1nZz
p3nGu1nZz / gist:4f0108fb137c0cd1a34fffe9fb205252
Created July 15, 2025 16:41
{"raw": "X-SPANFORMER\nSPAN-AwARE ENCODER\n5.4 Qualitative Span Interpretability\nTo assess the plausibility and semantic alignment of X-Spanformer's induced spans, we perform side-by-side comparisons against syntactic and semantic reference structures. Using single-sentence prompts drawn from the validation sets of WikiText and Stream-Mix, we visualize the top-K spans selected at various layers and entropy regimes. We benchmark span boundaries against:\nSyntactic parses: Constituents produced by Berkeley Neural Parser", "type": "mixed", "id": {"id": "a0409606-f532-4dd2-b02e-2a0bae5bfeee"}, "meta": {"status": "keep", "tags": [], "doc_language": "en", "extracted_by": "pdf2seg", "confidence": 0.78, "source_file": "XSpanformer_TokenizerFree_SpanAwareEncoder_RawsonChrzanowski_Preprint_v1.0_2025-06-26.pdf", "notes": "The segment contains a mix of technical terms and structured information that can be segmented into meaningful spans, such as \"X-SPANFORMER,\" \"SPAN-AwARE ENCODER,\" specific versions like \"5.4 Qua
@p3nGu1nZz
p3nGu1nZz / .py
Created December 2, 2024 14:14
EWC for fine-tuning models.
import torch
import torch.nn as nn
import torch.optim as optim
# Example model
class SimpleNN(nn.Module):
def __init__(self, input_size, hidden_size, output_size):
super(SimpleNN, self).__init__()
self.fc1 = nn.Linear(input_size, hidden_size)
self.fc2 = nn.Linear(hidden_size, output_size)
@p3nGu1nZz
p3nGu1nZz / gist:3acdf783cf14ec21d678db6fc04cc8ee
Created November 14, 2024 08:41
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Multiple Wobbly Plasma Bubbles</title>
</head>
<body>
@p3nGu1nZz
p3nGu1nZz / gist:6d603d674282a63c06f3c08457ca5ede
Created March 10, 2024 02:58
## You
hi copilot, attached is our first conversation together in a series of conversations about our MarsGame made in unity 2023 HDRP with netcode for gameobjects. We just implement the basic game system state machine and everything seems to be working, i will attach part 2 of our last conversation in the next prompt
## Copilot
Hello, I'm glad to hear that you are making progress on your MarsGame project. It sounds like an exciting and challenging endeavor. 😊
I have read the file you uploaded, which contains the first part of our conversation about your game. Here are some of the main topics we discussed:
- The game concept and setting: You explained that your game is a multiplayer survival game set on Mars, where players have to explore, gather resources, build bases, and fight enemies.
- The game engine and graphics: You chose to use Unity 2023 HDRP, which is a high-end rendering pipeline that supports realistic lighting, shadows, reflections, and materials. You also mentioned some of the assets and tools
@p3nGu1nZz
p3nGu1nZz / gist:93b498fe2a4f2bcf2ebf2506345587fc
Created March 1, 2024 18:50
using System;
using System.Collections.Generic;
using UnityEngine;
namespace HFSM
{
public abstract class StateMachine<T>
{
T ctx;
@p3nGu1nZz
p3nGu1nZz / gist:28fa2f5dd0d5659f7e0e106ed04a79cf
Created March 1, 2024 18:23
using System;
public class Singleton<T> where T : class, new()
{
// The single instance of the type T
private static readonly Lazy<T> instance = new(() => new T());
// The private constructor to prevent outside instantiation
public Singleton() { }
@p3nGu1nZz
p3nGu1nZz / gist:92bb6f3f11d332e9f7bfbc88efb7b11e
Created March 1, 2024 18:22
using System;
using System.Collections.Generic;
using UnityEngine;
namespace HFSM
{
public class StateMachine<T> : Singleton<StateMachine<T>>
{
T context;
@p3nGu1nZz
p3nGu1nZz / HFSM_csharp
Created May 30, 2022 23:10
using System;
using System.Collections;
using System.Collections.Generic;
using UnityEngine;
namespace HFSM
{
/// <summary>
/// Our General Purspose Hieracrhial State Machine Engine. This class allows
/// sub states to bind addition nodes of states to create a tree structure. We also