Inside PewDiePie's AI Assistant Odysseus: Local Models and Fine-Tuning Explained
Hugging Face · youtube · 2026-10-13
Hugging Face published a tutorial video breaking down how PewDiePie's self-built AI assistant Odysseus works:
- Agent harness from scratch: what an agent harness is, how tool calling works, and how to build your own.
- Running models locally: using llama.cpp (including the macOS app) and Hugging Face, with hosted hardware settings.
- Fine-tuning small models: fine-tuning models like Qwen3.5-9B (Unsloth GGUF) on agent traces so they call tools reliably in your own harness.
Full timestamps and resource links (GitHub repos, datasets, follow-up playlist) included.
More from coding & agent
- Claude Code Pushes Urgent Security Update Across All Installations — umeshonai · 2026-10-23
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- 3 flight-booking rules my AI agent checks that I'd never do by hand — Efistoffeles · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23