ingest(youtube): karpathy intro to LLMs tutorial + new tutorials category

AGENTS.md

@@ -40,6 +40,7 @@ knowledge-base/
 │   │   ├── directives/ ← Projekt-Direktiven (Pro-Leben, Qualität, Bot-Policy)
 │   │   └── agi/        ← AGI-bezogene Konzepte (Aschenbrenner, etc.)
 │   │   └── hardware/   ← Hardware-Frontier (Neuromorphic, Edge-Inferenz, etc.)
+│   ├── tutorials/      ← Lernpfade, Tutorials, Lernressourcen zu KI/LLMs
 │   ├── people/         ← Personen-Artikel (jede im Wiki erwähnte Person bekommt einen Eintrag)
 │   ├── institutions/   ← Institutionen, Organisationen, Firmen, Labs, Stiftungen, Unis — NICHT nur Companies
 │   ├── decisions/      ← Dated decisions

raw/youtube/2026-06-26_karpathy-how-i-use-llms.md

@@ -0,0 +1,74 @@
+---
+type: youtube
+source_url: https://www.youtube.com/watch?v=EWvNQjAaOHw
+retrieved: 2026-06-26
+channel: "Andrej Karpathy"
+title: "How I use LLMs"
+duration_sec: 7871
+has_transcript: false
+tags: [karpathy, llm, tutorial, llm-fundamentals, tool-integration, multimodal, voice-interaction, custom-gpts, context-window, thinking-models, learning-resource]
+---
+
+# How I use LLMs
+
+**Channel:** Andrej Karpathy
+**URL:** https://www.youtube.com/watch?v=EWvNQjAaOHw
+**Duration:** 2:11:11 (7871 sec)
+**Views:** ~2.5M (as of 2026-06-26)
+**Published:** ~1 year before retrieval (mid-2025)
+**Language:** English
+
+## Context
+
+Shared by k9ert in OME-Gruppe Topic 1345 ("Ich, der DAU und sein Bot LOGBUCH") on 2026-06-26. Recommended as a tutorial/learning resource for understanding AI/LLMs, especially for people wanting to learn about AI.
+
+## Summary
+
+*Reconstructed from YouTube metadata and web search summaries — no transcript available.*
+
+Andrej Karpathy's "How I use LLMs" is a practical, example-driven exploration of how to leverage Large Language Models in daily life and work. The video covers:
+
+### LLM Fundamentals
+- LLMs as AI systems trained on vast datasets
+- Pre-training for knowledge acquisition vs. post-training (fine-tuning) for alignment and specific tasks
+- The concept of a "knowledge cutoff" — models are only aware of information up to their training date
+- "Thinking models" that use reinforcement learning for improved accuracy
+
+### Core Interactions
+- Text-based interaction: prompts and AI-generated responses
+- Managing the "context window" (LLM's working memory)
+- Starting fresh chats for new topics to maintain accuracy and responsiveness
+
+### Tool Integration
+- Internet search to access up-to-date information beyond training data
+- Python interpreter for code execution and calculations
+- ChatGPT's Advanced Data Analysis for figures and plots
+- File uploads (documents, images — e.g., deciphering a blood test report)
+
+### Multimodal Capabilities
+- Audio interaction: speech-to-text input and text-to-speech output
+- Karpathy notes over half of his LLM interactions are voice-based for efficiency
+- Distinction between "fake audio" (TTS) and "true audio" (direct audio processing)
+- Image input including OCR and visual data analysis
+- Video input — querying models about real-world objects via camera
+
+### Personalization and Efficiency
+- "Custom instructions" to fine-tune LLM behavior and tone
+- "Custom GPTs" — specialized mini-LLMs for specific tasks (language learning, coding)
+- LLM memory — models remembering previous conversations within a chat
+
+## Why This Video Matters
+
+Karpathy is one of the most respected voices in AI education. His ability to explain complex topics clearly makes this video an excellent starting point for anyone wanting to understand LLMs practically — not just theoretically. The video bridges the gap between "what is an LLM" and "how do I actually use one effectively."
+
+## Related Wiki Pages
+
+- `[[wiki/concepts/llm/llm-knowledge-base.md]]` — Karpathy's wiki pattern (this repo's foundation)
+- `[[wiki/tutorials/karpathy-how-i-use-llms.md]]` — Tutorial wiki page for this video
+- `[[wiki/concepts/llm/llm-model-catalog.md]]` — Catalog of LLMs mentioned across the wiki
+- `[[wiki/concepts/llm/llm-sycophancy-confabulation.md]]` — LLM behavior pitfalls (relevant for practical usage)
+
+## Notes
+
+- `has_transcript: false` — No transcript was fetched for this ingest. Content summary reconstructed from YouTube metadata and web search results.
+- Karpathy also has a longer companion video "Deep Dive into LLMs like ChatGPT" (3:31:24, 7.7M views) at https://www.youtube.com/watch?v=7xTGNNLPyMI — referenced as related content.

scripts/wiki-lint-report.md

@@ -1,6 +1,6 @@
 # Wiki Lint Report
 
-*Generated: 2026-06-25 18:03:53 UTC*
+*Generated: 2026-06-26 08:05:13 UTC*
 *Repo: /home/node/workspace/knowledge-base*
 *Script: scripts/wiki-lint.sh v1.0*
 
@@ -15,23 +15,24 @@
 | wiki/concepts/agi | 2 | ✅ |
 | wiki/concepts/directives | 4 | ✅ |
 | wiki/concepts/hardware | 3 | ✅ |
-| wiki/concepts/llm | 14 | ⚠️ warn (refactor) |
+| wiki/concepts/llm | 15 | ⚠️ warn (refactor) |
 | wiki/concepts/policy | 9 | ✅ |
 | wiki/decisions | 2 | ✅ |
 | wiki/events | 4 | ✅ |
 | wiki/ideas | 4 | ✅ |
 | wiki/institutions | 23 | ❌ FAIL (refactor) |
-| wiki/people | 9 | ✅ |
+| wiki/people | 37 | ❌ FAIL (refactor) |
 | wiki/teams | 3 | ✅ |
 | wiki/tools | 11 | ✅ |
+| wiki/tutorials | 1 | ✅ |
 
 _Schema v1.5 Sub-Categories: `concepts/hardware`, `concepts/agi`, `people/`, `institutions/` (alle in Counts oben enthalten)_
 
 ### Stub-Quote (<30 Zeilen)
-⚠️ **27 / 113 (23%)** — threshold 10%
+⚠️ **21 / 143 (14%)** — threshold 10%
 
 ### Frontmatter Präsenz
-✅ **110 / 113 present**
+✅ **140 / 143 present**
 
 ### Broken Cross-References
 ✅ **0 broken**
@@ -40,20 +41,25 @@ _Schema v1.5 Sub-Categories: `concepts/hardware`, `concepts/agi`, `people/`, `in
 ✅ **0 orphans**
 
 ### Dup-Topic Cluster (substantielle Vorkommen)
-⚠️ **polymarket**: 7 Files (≥3 Vorkommen je File)
+⚠️ **polymarket**: 8 Files (≥3 Vorkommen je File)
   - `wiki/concepts/agents/ai-trading-hub.md` (4 Treffer)
   - `wiki/concepts/agents/polymarket-arbitrage.md` (12 Treffer)
   - `wiki/concepts/agents/polymarket-hub.md` (8 Treffer)
-  - `wiki/institutions/polymarket.md` (6 Treffer)
+  - `wiki/institutions/polymarket.md` (7 Treffer)
+  - `wiki/people/shayne-coplan.md` (8 Treffer)
   - `wiki/teams/ruediger.md` (8 Treffer)
   - `wiki/tools/fincept-terminal.md` (3 Treffer)
   - `wiki/tools/polymarket-monitoring-bot.md` (11 Treffer)
-⚠️ **lightning**: 9 Files (≥3 Vorkommen je File)
+⚠️ **lightning**: 13 Files (≥3 Vorkommen je File)
   - `wiki/concepts/agents/agent-payments-lightning.md` (15 Treffer)
   - `wiki/concepts/agents/lightning-payments-hub.md` (11 Treffer)
-  - `wiki/institutions/alby.md` (5 Treffer)
+  - `wiki/institutions/alby.md` (6 Treffer)
-  - `wiki/institutions/blink-wallet.md` (4 Treffer)
+  - `wiki/institutions/blink-wallet.md` (5 Treffer)
-  - `wiki/institutions/lightning-labs.md` (7 Treffer)
+  - `wiki/institutions/lightning-labs.md` (8 Treffer)
+  - `wiki/people/elizabeth-stark.md` (8 Treffer)
+  - `wiki/people/moritz-kaminski.md` (6 Treffer)
+  - `wiki/people/nicolas-burtey.md` (3 Treffer)
+  - `wiki/people/olaoluwa-osuntokun.md` (9 Treffer)
   - `wiki/teams/netbits-stachelbanane.md` (5 Treffer)
   - `wiki/tools/blink-wallet-skill.md` (4 Treffer)
   - `wiki/tools/fincept-terminal.md` (3 Treffer)
@@ -86,7 +92,7 @@ _Schema v1.5 Sub-Categories: `concepts/hardware`, `concepts/agi`, `people/`, `in
   - `wiki/concepts/agents/polymarket-arbitrage.md` (6 Treffer)
   - `wiki/concepts/agents/polymarket-hub.md` (4 Treffer)
   - `wiki/concepts/directives/openclaw-financial-bots-policy.md` (4 Treffer)
-  - `wiki/institutions/fincept.md` (4 Treffer)
+  - `wiki/institutions/fincept.md` (5 Treffer)
   - `wiki/teams/rene-kl.md` (3 Treffer)
   - `wiki/teams/ruediger.md` (4 Treffer)
   - `wiki/tools/fincept-terminal.md` (5 Treffer)
@@ -95,15 +101,15 @@ _Schema v1.5 Sub-Categories: `concepts/hardware`, `concepts/agi`, `people/`, `in
 ✅ **0 stale**
 
 ### Uncovered Raw Sources
-✅ **43 raw, all covered**
+✅ **46 raw, all covered**
 
 ## Summary
 
-- Total Wiki-Pages: 113
+- Total Wiki-Pages: 143
-- Issues: 1
+- Issues: 2
 
 → **Action needed**: subagent spawn for fixes. See '## Recommended Subagent Spawns'.
 
 ## Recommended Subagent Spawns
 
-- **stub-killer** — 27 stubs (23%, threshold 10%)
+- **stub-killer** — 21 stubs (14%, threshold 10%)

wiki/index.md

@@ -2,7 +2,7 @@
 
 *Auto-generated: 2026-06-23*
 
- *Letzte Aktualisierung: 2026-06-26 (35. Update — Nano Banana Incident: LLM Sycophancy, Confabulation & Session-Statelessness. Neue Wiki-Seite `concepts/llm/llm-sycophancy-confabulation.md`. Raw-Datei `other/2026-06-26_nanobana-incident-sycophancy-confabulation.md`.)*
+ *Letzte Aktualisierung: 2026-06-26 (36. Update — Neue Kategorie `wiki/tutorials/`: Karpathy "How I use LLMs" als erste Lernressource. Raw-Datei `youtube/2026-06-26_karpathy-how-i-use-llms.md`.)*
 
 ## Architecture
 
@@ -183,6 +183,12 @@
 | [OME21 Afterhour: Makro-Systematik](events/ome21-afterhour-makro-systematik.md) | Club 77.7 NotebookLM-Briefing (15 S.): Systemanalyse alternativer Paradigmen — UAP-Herkunftshypothesen, Handelsrecht vs. Naturrecht, Meritokratie, Tribalismus, dezentrale KI als Gegenmacht, Synthese (Zero Compromise) | other/2026-06-19_ome21-afterhour-makro-systematik.md |
 | [OME22 — KI-Nacht & Agenten-Architektur](events/ome22-ki-nacht-agenten-architektur.md) | NotebookLM-Infografik: Hochsicherheits-Rechenzentrum Hannover, lokale Agenten ohne Internet, 66% KI-Misserfolgsquote, Pluribus-Memory-Layer, Qwen Agent World, OpenClaw-Produktions-Agenten, Guardrail-Dilemma, Tool-Vergleich (NBN/OpenClaw/Pluribus) | other/2026-06-25_ome22-ki-nacht-agenten-architektur.md |
 
+## Tutorials
+
+| Seite | Beschreibung | Quellen |
+|-------|-------------|---------|
+| [Karpathy — How I use LLMs](tutorials/karpathy-how-i-use-llms.md) | Praxis-Crashkurs von Andrej Karpathy (2h11m, 🇬🇧 English): LLM Fundamentals, Tool Integration, Multimodal (Audio/Image/Video), Custom GPTs, Personalization. Lernpfad für LLM-Verständnis | youtube/2026-06-26_karpathy-how-i-use-llms.md |
+
 ## Raw Sources
 
 | Datei | Typ | Titel |
@@ -221,3 +227,4 @@
 | `raw/youtube/2026-06-24_peter-yang-hermes-full-course.md` | youtube | Hermes Full Course: Build Your 24/7 AI Chief of Staff in 45 Minutes (Peter Yang, 24.06.2026) |
  | `raw/other/2026-06-25_ome22-ki-nacht-agenten-architektur.md` | other | OME22 — KI-Nacht & Agenten-Architektur: Der Realitätscheck (NotebookLM-Infografik: Hannover-Rechenzentrum, lokale Agenten, 66% Misserfolgsquote, Pluribus, OpenClaw, Guardrail-Dilemma) |
  | `raw/blog/2026-06-25_binaryverseai-qwen-agentworld.md` | blog | BinaryVerse AI: Qwen AgentWorld Explained — Predict Before Agents Act (AgentWorldBench scores, CPT/SFT/RL pipeline, 7 domains, GUI text representation) |
+| `raw/youtube/2026-06-26_karpathy-how-i-use-llms.md` | youtube | Andrej Karpathy: How I use LLMs (2:11:11, ~2.5M views, English) — Praxis-Crashkurs: LLM Fundamentals, Tool Integration, Multimodal, Custom GPTs |

wiki/log.md

@@ -2,6 +2,19 @@
 
 *Append-only changelog. Start: 2026-06-05*
 
+## [2026-06-26] Ingest | Karpathy — "How I use LLMs" (Tutorial + New Category `wiki/tutorials/`)
+**Type:** ingest | **Scope:** raw/youtube, wiki/tutorials (NEW), wiki/index, AGENTS.md
+**Source:** YouTube — https://www.youtube.com/watch?v=EWvNQjAaOHw
+**Trigger:** Shared by k9ert in OME-Gruppe Topic 1345 ("Ich, der DAU und sein Bot LOGBUCH") on 2026-06-26. Recommended as tutorial/learning resource for understanding AI/LLMs.
+**Actions:**
+- raw: `raw/youtube/2026-06-26_karpathy-how-i-use-llms.md` (created — 3.7 KB; Frontmatter [type: youtube, has_transcript: false], reconstructed summary from YouTube metadata + web search, 5 content sections: LLM Fundamentals, Core Interactions, Tool Integration, Multimodal Capabilities, Personalization & Efficiency, Lernpfad, Cross-Refs to 6 wiki pages)
+- wiki (NEW CATEGORY + PAGE): `tutorials/karpathy-how-i-use-llms.md` (created — 4.3 KB; erste Seite in neuer `wiki/tutorials/` Kategorie. Frontmatter, Überblick-Tabelle, Zielgruppe, 5 Inhalts-Sektionen, Lernpfad-Grafik mit Companion-Video, 6 Cross-Refs, 5 externe Links, Quellen-Attribution)
+- wiki: `index.md` (updated — Header auf "36. Update", neue Tutorials-Sektion mit erstem Eintrag vor Raw Sources, neuer Raw-Sources-Eintrag)
+- AGENTS.md: Directory-Structure-Diagramm aktualisiert — `tutorials/` Ordner mit Beschreibung "Lernpfade, Tutorials, Lernressourcen zu KI/LLMs" hinzugefügt
+- log: this entry
+**Video identifiziert:** "How I use LLMs" von Andrej Karpathy (2:11:11, ~2.5M views, English). Kein "Intro to Large Language Models" wie ursprünglich vermutet — das Video ist ein Praxis-Crashkurs über LLM-Nutzung (Fundamentals, Tools, Multimodal, Custom GPTs), kein reines Intro. Karpathy hat auch ein längeres Companion-Video "Deep Dive into LLMs like ChatGPT" (3:31:24, 7.7M views, https://www.youtube.com/watch?v=7xTGNNLPyMI).
+**Subagent-Modell:** ollama/glm-5.2:cloud
+
 ## [2026-06-26] Ingest | The Nano Banana Incident — LLM Sycophancy, Confabulation & Session-Statelessness
 **Type:** ingest | **Scope:** raw/other, wiki/concepts/llm, wiki/index
 **Source:** OME-Gruppe, Topic "TechnicalIssues", 26.06.2026 — Diskussion zwischen Rüdiger (@Stelariz_75), Hector (@Hector_newbutlerbot) und Gemini (referenziert)

wiki/tutorials/karpathy-how-i-use-llms.md

@@ -0,0 +1,102 @@
+---
+created: 2026-06-26
+updated: 2026-06-26
+sources:
+  - youtube/2026-06-26_karpathy-how-i-use-llms.md
+tags: [tutorial, llm, karpathy, learning-resource, llm-fundamentals, multimodal, tool-integration, english]
+---
+
+# Tutorial: Andrej Karpathy — "How I use LLMs"
+
+> **📌 Lernressource** — Erste Seite in der `wiki/tutorials/` Kategorie.
+
+## Überblick
+
+| Feld | Wert |
+|------|------|
+| **Titel** | How I use LLMs |
+| **Autor** | [Andrej Karpathy](https://www.youtube.com/@AndrejKarpathy) |
+| **URL** | https://www.youtube.com/watch?v=EWvNQjAaOHw |
+| **Dauer** | 2:11:11 |
+| **Sprache** | 🇬🇧 English |
+| **Aufrufe** | ~2.5M |
+| **Veröffentlicht** | ~Mitte 2025 |
+| **Raw-Datei** | [raw/youtube/2026-06-26_karpathy-how-i-use-llms.md](../raw/youtube/2026-06-26_karpathy-how-i-use-llms.md) |
+
+## Zielgruppe
+
+Dieser Crashkurs richtet sich an **Lernende, die LLMs praktisch verstehen wollen** — von Anfängern, die gerade erst mit ChatGPT/Claude starten, bis zu Entwicklern, die ihre Workflow-Effizienz steigern möchten. Karpathy erklärt von Grundlagen bis zu fortgeschrittenen Features wie Custom GPTs und Multimodalität.
+
+Kein Vorwissen erforderlich. Karpathy ist bekannt für seine Fähigkeit, komplexe KI-Themen zugänglich zu erklären.
+
+## Inhalt
+
+### 1. LLM Fundamentals
+- Was sind LLMs? Wie werden sie trainiert?
+- **Pre-training** (Wissenserwerb) vs. **Post-training / Fine-tuning** (Alignment, Tasks)
+- **Knowledge Cutoff**: Modelle wissen nur bis zum Trainingsdatum
+- **Thinking Models**: RL-basiertes "Nachdenken" für bessere Genauigkeit
+
+### 2. Core Interactions
+- Text-basierte Interaktion: Prompts & Responses
+- **Context Window** als Working Memory verwalten
+- Frische Chats für neue Topics = bessere Genauigkeit
+
+### 3. Tool Integration
+- **Internet Search** — aktuelle Infos über das Training-Datum hinaus
+- **Python Interpreter** — Code-Ausführung, Berechnungen
+- **Advanced Data Analysis** — Diagramme, Plots
+- **File Uploads** — Dokumente, Bilder (z.B. Bluttest-Analyse)
+
+### 4. Multimodal Capabilities
+- **Audio**: Speech-to-Text Input, Text-to-Speech Output
+- Karpathy: >50% seiner Interaktionen sind voice-based
+- "Fake Audio" (TTS) vs. "True Audio" (direkte Audio-Verarbeitung)
+- **Image Input**: OCR, visuelle Datenanalyse
+- **Video Input**: Modelle über Kamera reale Objekte abfragen
+
+### 5. Personalization & Efficiency
+- **Custom Instructions**: Verhalten & Ton anpassen
+- **Custom GPTs**: Spezialisierte Mini-LLMs (Sprachen lernen, Coding)
+- **LLM Memory**: Conversationen über Chats hinweg merken
+
+## Warum als Lernressource?
+
+**Karpathy ist einer der kompetentesten KI-Educators.** Seine Videos kombinieren:
+- ✅ Tiefe technische Understanding (ex-Tesla AI Director, OpenAI founding member)
+- ✅ Klarheit — komplexe Themen zugänglich erklärt
+- ✅ Praxisbezug — echte Workflows, keine Theorie-only-Vorträge
+- ✅ Aktualität — deckt 2025er Features ab (thinking models, true audio, custom GPTs)
+
+## Lernpfad
+
+```
+"How I use LLMs" (dieses Video, 2h11m)
+       ↓
+"Deep Dive into LLMs like ChatGPT" (Karpathy, 3h31m, 7.7M views)
+  → https://www.youtube.com/watch?v=7xTGNNLPyMI
+       ↓
+Praxis: Eigenes LLM-Wiki aufbauen (siehe llm-knowledge-base.md)
+```
+
+## Cross-References
+
+- [[../concepts/llm/llm-knowledge-base.md]] — Karpathy's Wiki-Pattern, die Grundlage dieses Repos
+- [[../concepts/llm/llm-model-catalog.md]] — Katalog aller im Wiki erwähnten LLMs
+- [[../concepts/llm/llm-sycophancy-confabulation.md]] — LLM-Verhaltensfallen in der Praxis
+- [[../concepts/llm/llm-behavior-persistence.md]] — Persistente Verhaltensmuster
+- [[../concepts/llm/flat-curve-society.md]] — Yegge's "Discernment Horizon" (warum LLM-Literacy wichtig wird)
+- [[../architecture/model-routing.md]] — Wie wir LLMs in OpenClaw routen
+
+## Externe Links
+
+- **Video:** https://www.youtube.com/watch?v=EWvNQjAaOHw
+- **Karpathy's YouTube Channel:** https://www.youtube.com/@AndrejKarpathy
+- **Karpathy's X/Twitter:** https://x.com/karpathy
+- **Companion Video ("Deep Dive into LLMs like ChatGPT"):** https://www.youtube.com/watch?v=7xTGNNLPyMI
+- **Karpathy Gist (LLM Wiki Pattern):** https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f
+
+## Quelle
+
+- **Shared by:** k9ert in OME-Gruppe Topic 1345 ("Ich, der DAU und sein Bot LOGBUCH"), 2026-06-26
+- **Kontext:** Empfohlen als Lernressource für KI/LLM-Verständnis