---
title: "Self-Training Agents: Hermes Agent, HF Traces, Skills, MCP & Finetuning  — Merve Noyan, Hugging Face"
category: "resources"
sourceLabels: ["Public YouTube metadata"]
---
# Self-Training Agents: Hermes Agent, HF Traces, Skills, MCP & Finetuning  — Merve Noyan, Hugging Face

## What It Is
A public YouTube video used as supporting context for the AI Engineer World's Fair 2026 wiki. It is not part of the confirmed World's Fair San Francisco 2026 official event-video set.

## Source Classification
- Source role: supporting contextual video source.
- Channel/source: public YouTube or AI Engineer channel video outside the confirmed World's Fair San Francisco 2026 event-video set.
- Use: background, speaker, company, or historical AIE context; not primary evidence for World's Fair San Francisco 2026 session facts.

## Transcript Availability
English auto-captions

## Cached Transcript
Not fetched yet.

## Link
[YouTube](https://www.youtube.com/watch?v=OV56RddyFuU)

## Related Scheduled Sessions
- [[2026-06-29-merve-noyan-skill-issue-stop-deploying-vision-language-models-use-them-with-skills-to-build-e2e-vision-apps-on-edge]] — Skill issue: stop deploying vision language models, use them with Skills to build e2e vision apps on edge
- [[2026-07-01-chris-alexiuk-compression-at-the-edge]] — Compression at the Edge
- [[2026-07-01-chris-alexiuk-compression-at-the-edge]] — Compression at the Edge
## Extracted Slides
- [[youtube-OV56RddyFuU-dense-slides]]
- [[youtube-OV56RddyFuU-reconstructed-slides]]
- [[youtube-OV56RddyFuU-slides]]