New Claude Desktop + Ollama Update is INSANE!

You are helping me turn one specific YouTube video into real, durable learning.

Source video:
- Title: New Claude Desktop + Ollama Update is INSANE!
- URL: https://www.youtube.com/watch?v=-bO6uzhTAas
- Topic: Interfaces + Open Design
- My current learning frame: Install Ollama, wire Claude Code to a local Qwen-7B-Chat model via the two environment variables on localhost:11434, then swap the --model flag to compare it against GPT-OSS-7B on the same refactoring prompt offline.
- Why this matters: New playlist item from Julian Goldie SEO; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:00 / Evidence 1: "New Claude Desktop plus Ollama update is insane. What if you could run Claude Desktop with free local models on your own computer? Ollama just dropped an update that flips the whole game. Most people have no idea..."
- 2:52 / Evidence 2: "website and grab the download for your system. Mac, Windows, and Linux all work. Once Ollama is running on your machine, you have two paths. Path one Claude Code with local models. You install Claude Code with one..."
- 5:30 / Evidence 3: "drop in images and get the model to describe or analyze them. That's the full feature set you'd expect from a top-tier AI tool, but now it's working with open-source models. Let me give you some real ways..."
- 7:11 / Evidence 4: "instead. Good news is that everything else works. Co-work, Claude Code, sub-agents. Then, your Ollama Cloud models show up automatically. There's also a third-party project worth knowing about. There's an open-source tool on GitHub called Claude Desktop LLM..."
- 8:47 / Evidence 5: "SOPs, and 100 plus AI use cases like this one, join the AI Success Lab. Links in the comments and description. You'll get all the video notes from there, plus access to our community of 58,000 members who..."

Video-aware target:
- Prompt lane: Local model/runtime
- Mechanism to extract: Identify why the local setup works or fails for this specific agent task, not whether local models are generally good.
- Artifact to produce: A local model/runtime fit sheet with hardware constraints, model choice, endpoint setup, task benchmark, and fallback rule.
- Artifact must include: hardware; runtime; model/quantization; endpoint; agent integration; benchmark/fallback

Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Identify why the local setup works or fails for this specific agent task, not whether local models are generally good. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A local model/runtime fit sheet with hardware constraints, model choice, endpoint setup, task benchmark, and fallback rule.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Task -> Hardware -> Model/quantization -> Runtime endpoint -> Agent tool loop -> Benchmark task -> Fallback
   - answers to these source questions: What machine/runtime is shown? | What task exposes the model limit? | What setup change improves the loop?
   - 3 concrete examples that apply the video idea to real agentic work, such as Ollama or LM Studio coding endpoint; MLX Apple Silicon runner; DGX-backed Hermes session
   - 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: using a local model like ChatGPT; ignoring latency/context limits; no benchmark task
   - a checklist for the next real workflow, focused on: task fit, runtime setup, latency/context, tool loop, fallback
   - one practical exercise with a clear done signal: Choose one real coding task and specify the pass/fail benchmark for a local model.
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.

Quality bar:
- Make this specific to "New Claude Desktop + Ollama Update is INSANE!", not a generic Interfaces + Open Design essay.
- Tie each harness element to a transcript anchor that names a tool, state boundary, permission, model behavior, or verification step.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: local-model ideology; hardware specs without workflow fit; benchmarks unrelated to the actual task.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.