Skip to content

Instantly share code, notes, and snippets.

Discover gists

@FreeRiverHouse
FreeRiverHouse / kalshi-autotrader.py
Created February 22, 2026 20:33
Kalshi AutoTrader - review request
#!/usr/bin/env python3
"""
Kalshi AutoTrader - Unified Edition
Consolidation of v1 (crypto), v2 (infra+weather+momentum), v3 (LLM pipeline)
Architecture: FORECASTER → CRITIC → TRADER
├─ LLM forecaster (Claude via Anthropic/OpenRouter) when API key available
├─ Heuristic forecaster (sport-specific + crypto models) as fallback
├─ Weather forecaster (NWS integration from v2)
├─ Crypto signal enrichment (sentiment, momentum, regime from v2)
@karpathy
karpathy / llm-wiki.md
Created April 4, 2026 16:25
llm-wiki

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.