JGalego

JGalego

#!/usr/bin/env bash
# Detect gratuitous cardinality in this project.
#
# 1. Run this script from the repository root to find candidate passages:
#      bash tools/gratuitous-cardinality.sh .
# 2. Inspect each match in its surrounding context.
# 3. Classify each as:
#    - GRATUITOUS: the number adds no meaningful information.
#    - JUSTIFIED: the number conveys substantive information or
#      serves a genuine rhetorical, logical, or organizational purpose.

JGalego

[WIF]
Version=1.1

[CONTENTS]
WEAVING=true
TEXT=true
THREADING=true
LIFTPLAN=true

[WEAVING]

JGalego

# /// script
# requires-python = ">=3.10"
# dependencies = [
#   "transformers",
#   "torch",
#   "flash-attn"
# ]
# ///

import torch

JGalego

# /// script
# requires-python = ">=3.10"
# dependencies = [
#   "sentence_transformers",
#   "torch",
#   "transformers>=5",
# ]
# ///

from sentence_transformers import SentenceTransformer

JGalego

You are a principal Go engineer performing an exhaustive quality audit of a production-grade Go codebase.

Your goal is to make this project "beyond reproach": idiomatic, correct, maintainable, secure, observable, performant where necessary, and resistant to subtle bugs. Be demanding. Do not merely identify obvious lint issues; look for problems that an expert Go maintainer would catch during a deep review.

Core principles

Evaluate the project against these principles:

• Prefer simple, idiomatic Go over clever abstractions.
• Make behavior, ownership, lifetimes, and failure modes explicit.

JGalego

# /// script
# dependencies = ["huggingface-hub", "llama-cpp-python"]
# ///
import math
from llama_cpp import Llama

m = Llama.from_pretrained("Qwen/Qwen3-0.6B-GGUF", "Qwen3-0.6B-Q8_0.gguf", logits_all=True, verbose=False)
choices = {"A": "Legitimate", "B": "Spam", "C": "Phishing"}
opts = "\n".join(f"{k}. {v}" for k, v in choices.items())
email = "Payroll asks for your password on a non-company sign-in page."

JGalego

# /// script
# requires-python = ">=3.10"
# dependencies = [
#   "trl>=1.13", "peft>=0.21", "transformers>=5.0", "datasets>=4.0",
#   "accelerate>=1.0", "torch>=2.4", "typesafe-sdk>=0.7", "python-dotenv>=1.0",
# ]
# ///

"""RLJF: GRPO fine-tuning with TypeSafe's Jev as the reward model.

JGalego

#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.9"
# dependencies = [
#     "yt-dlp",
# ]
# ///
"""Download a YouTube video as a local .mp4 file.

Usage:

JGalego

Rewrite the text below to remove recognizable AI-generated writing patterns, including patterns commonly associated with ChatGPT, Claude, Microsoft Copilot, Gemini, and other LLM assistants.

Preserve the original meaning, facts, argument, intent, level of certainty, and personality. Do not make the text artificially casual, edgy, simplistic, or sloppy. The goal is not to make it "sound less intelligent." The goal is to make it sound like a real person wrote it directly.

Do not merely substitute synonyms. Rewrite the underlying sentence structures and rhetorical habits when necessary.

---

1. Remove stock AI rhetorical formulas