The Full Stack (fullstackdeeplearning.com) vs JanitorAI

Lecture pages and resources covering prompt engineering, augmented language models, LLMOps, and language UI/UX.

Multi-year course content on infrastructure, data management, deployment, monitoring, and ML team organization.

Current material on collaborating with and building agent-based systems, including a perspective on multiplayer AI.

A maintained guide to cloud GPU options that helps teams choose compute for training and inference.

Provides unlimited free character chats powered by JanitorAI's in-house LLM (~9K context window on free accounts), with a toggleable JLLM-short mode for snappy, dialogue-focused replies that are 70% shorter.

Lets Janitor+ subscribers tap directly into third-party frontier models via a built-in per-token wallet at a 10% discount, while keeping full BYOK reverse-proxy support with config duplication and reasoning tag display.

Allows creators to build complex characters up to 1 MB in size with multiple intro scenarios and programmable Scripts that trigger dynamic lore or behavioral rules using whole-word matching and built-in debugging tools.

Exposes low-level sampling parameters in the chat menu, including custom Top-K, Top-P, frequency and repetition penalties, forbidden vocabulary lists, and response prefill instructions.