hector-bot/knowledge-base
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
130 commits 1 branch 0 tags 7.1 MiB
Commit graph

14 commits

Author SHA1 Message Date
Hector
22c5d016d7 feat: DeRonin Chinese AI Stack — 87% cost-cut field report 
- raw: raw/xpost/2026-06-29_deronin-chinese-ai-stack-cost-savings.md (NEW)
- wiki: concepts/llm/chinese-model-cost-routing.md (NEW — 8.5 KB)
  - Swap matrix: Opus→Kimi, GPT→Qwen, Sonnet→GLM, GPT-mini→MiMo, GPT-Image→Wan, Sora→Kling
  - Barbell routing connection + Hector-vs-DeRonin comparison
  - Factory-for-Gods thesis validation with empirical data
  - Cross-refs to 8 wiki pages + model-router skill
- wiki: index.md (updated — 43. Update)
- wiki: log.md (updated)
 2026-06-29 19:34:04 +02:00
Hector
fd39380f28 ingest(raw): roemmele-warning-open-source-ai-banned 
Follow-up to ReDS post (2026-06-28): 'I tried to warn ya' — September 2024
warning vindicated. Narrative arc: Alarm (2024) → ReDS concept → grim vindication.
New raw file, updated 4 wiki pages, index+log.
 2026-06-29 12:30:03 +02:00
Hector
19f91f7309 ingest(xpost): roemmele-reds-decentralized-ai-vs-amodei 
- raw: raw/xpost/2026-06-28_roemmele-reds-decentralized-ai-vs-amodei.md (NEW)
- wiki NEW: concepts/llm/reds-resilient-decentralized-swarm.md (ReDS concept page)
- wiki UPDATE: people/brian-roemmele.md (ReDS section, +1 source, +1 X-post)
- wiki UPDATE: people/dario-amodei.md (ReDS critique section, +1 source)
- wiki UPDATE: concepts/policy/ai-regulation-2026.md (centralization vs decentralization debate)
- wiki UPDATE: concepts/llm/decentralized-ai-counterpower.md (ReDS extension section)
- wiki UPDATE: index.md (41. update, new ReDS entry, updated people entries)
- log: entry appended

Source: https://x.com/brianroemmele/status/2071238497483297138
Shared by Pit Weber in OME-Gruppe Topic 'Krallenpolitik' (Topic 1774)
 2026-06-28 23:44:50 +02:00
Hector
c35d8e0736 ingest(xpost): Hermes Mixture of Agents (MoA) — multi-model fusion feature 
- raw: raw/xpost/2026-06-28-hermes-moa-vaibhavsisinty.md (NEW)
- wiki: tools/hermes-desktop.md (updated — new MoA section: architecture, performance, composability, criticism, OpenRouter Fusion comparison)
- wiki: index.md (updated — 38th update, Hermes Desktop row updated, new raw source)
- wiki: log.md (new entry)

Source: @VaibhavSisinty X post, shared by Pit Weber in OME Topic 3770 (Hermès Agents), 2026-06-28
 2026-06-28 13:33:49 +02:00
Hector
a61ca95bc6 ingest(xpost): AMD Ryzen AI Edge-Inferenz WMT-008 
- raw/xpost/2026-06-16_amd-ryzen-ai-edge-inferenz.md (new)
- wiki/concepts/hardware/edge-inference-als-cloud-alternative.md (new)
- Cross-Refs: cloud-exit-and-local-superiority.md, neuromorphic-chips-und-quantencomputer.md, ai-value-migration-orchestration.md
- wiki/index.md updated with new Hardware page
- WMT-008: Lisa Su lunchbox PC, 235B local, 128GB unified memory, 3x RTX 5080
 2026-06-23 13:19:24 +02:00
Hector
2d36e8968a ingest(xpost): brian-roemmele-ki-psychologische-tests 2026-06-22 17:42:25 +02:00
Hector
d6ef97a9b5 wikify: TheProphet 'AI-Deal-Breaks-Chart' (Intelligence Commoditization Thesis) 
- raw/xpost/2026-06-18_theprophet-ai-deal-breaks-chart.md (new, 6.2 KB)
- wiki/concepts/llm/ai-intelligence-commoditization-thesis.md (new, 11.7 KB)
  Scharnier zwischen TheProphet (geopolitisch-industrialisiert),
  Aravind/Srinivas (Investor/Orchestration), Miles Deutscher
  (Weaponization), Aschenbrenner (US-Industrialisierung)
- wiki/concepts/llm/ai-value-migration-orchestration.md (extended)
  Geopolitische Schicht + Cross-Link zur Scharnier-Seite
- wiki/index.md (Header + neue Zeile)
- wiki/log.md (17. Update)

Trigger: Pit Weber msg #6831 in OME Topic 13 (News & Infos), 2026-06-18 22:35 UTC.
Push wartet auf WMT-007 (Forgejo-Token-Rotation).
 2026-06-18 22:39:25 +02:00
Hector
8421be26c8 ingest(xpost): milesdeutscher fable-weaponization 2026-06-18 
- raw/xpost/2026-06-18_milesdeutscher-fable-weaponization.md: 9 Thesen + Top-Kommentare + Pit-Context + Hector-Vorab-Einordnung
- wiki/concepts/policy/ai-as-geopolitical-weapon.md: neue Konzeptseite, 9 Thesen mit Quellenverweis + Hector-Einordnung (Stärken/Schwächen/Netto), Cross-Refs zu AI Regulation, Biosecurity, Aschenbrenner, Anthropic, OpenAI, Open-Source-LLMs
- wiki/concepts/policy/ai-regulation-2026.md: updated, neue Source, Geopolitik-Cross-Link ergänzt
- wiki/index.md: Header auf 2026-06-18, neue Policy-Sektion-Zeile
- wiki/log.md: 2026-06-18-Eintrag

Trigger: Pit Weber Thread-Share im OME-Krallenpolitik-Topic am 2026-06-18 14:13 UTC.
Wikify via Main-Loop (Subagent-Pfade xai+moonshot waren kaputt: Billing/401).

Wiki-Page: https://vmd185580.tailf38284.ts.net/hector-bot/knowledge-base/wiki/concepts/policy/ai-as-geopolitical-weapon.md
Lint: 0 issues / 52 files
 2026-06-18 16:21:39 +02:00
Hector
507d144c0e ingest(xpost): harrystebbings-20vc-aravind-srinivas 
20VC-Podcast mit Aravind Srinivas (Perplexity CEO, 15.06.2026, London).
Harry Stebbings X-Post-Summary mit allen 7 Notizen inkl. Micron > Meta,
Token Value per Watt per User, Export Controls halfen China, Dario
Disservice an AI.

Zentrales Konzept identifiziert: AI Value Migration - Wert verschiebt
sich 2026 von Frontier-Modellen zu:

  1. Orchestrierung & Agent-Harnesses (Fusion, MCP, Sub-Task-Routing)
  2. Physische Infrastruktur (Strom, Speicher, Rechenzentren)
  3. Mindset (Speed + Humility + Bottleneck-Disziplin)

Modelle werden zur Commodity. Chinesische Open-Source-Modelle (Kimi K2.7,
GLM 5.2, DeepSeek) schliessen die Luecke. OpenRouter Fusion + Self-Fusion
+6.7% zeigen Orchestrierungs-Lift ohne neue Modellkosten.

Cross-References zu allen bestehenden Concept-Seiten:
- llm-model-fusion-ensembles (Orchestrator-Pattern)
- ai-regulation-2026 (Export Controls, jetzt in concepts/policy/)
- glm-5.2-zai-coding-model (chinesisches Open-Source als Beleg)
- llm-behavior-persistence (Modell-Behavior als strategisches Asset)
- real-world-coding-showdown (Sub-Task-Routing)
- quality-standard (Speed + Vollstaendigkeit)
- pro-leben-directive (Pro-Leben-Perspektive)

Subagent hatte zwischenzeitlich Refactor durchgefuehrt (concepts/ in
concepts/llm/, agents/, policy/, directives/). Neue Datei nach
concepts/llm/ einsortiert, Cross-References aktualisiert.

Pro-Leben-Konsequenz: Mehrere Spielfelder = mehr Akteure = mehr
Handlungsfaehigkeit. Orchestrierung ist direkter Handlungsraum fuer
OpenClaw. Exportkontrollen langfristig kontraproduktiv - Open Source +
Orchestration ist robustere Strategie.
 2026-06-15 16:51:48 +02:00
Hector Bot
7aace389c1 ingest(xpost): lieselweppen-llm-behavior-persistence 
Konzeptseite zu Persistenz gelernter Verhaltensweisen in LLMs.
Basiert auf Liesel Weppens 8 Suchbegriffen (Sleeper Agents, Backdoor
safety training, machine unlearning bias, bias persistence, bias
transfer, persistent backdoors, catastrophic forgetting, limits of
debiasing). Drei Achsen: versteckte Verhaltensmuster überleben
Safety-Training, Machine Unlearning entfernt Bias unvollstaendig,
catastrophic forgetting als Daempfer.

Kernthese: Open Weights != Open Model — Pro-Leben-Perspektive mit
realistischen Handlungsspielraumen (Open + Audit, selektive
Offenlegung, verteilte Sicherheit, Engineering-Realismus).

Subagent-Initial-Versuch scheiterte (xai billing error); manuell
finalisiert im Main-Loop.
 2026-06-15 06:55:43 +02:00
Hector Bot
58ed176439 ingest(xpost): Brian Roemmele - Anthropic Selbstzerstörung, Kundenabwanderung, IPO-Schaden 2026-06-13 19:19:39 +02:00
Hector Bot
2328b1c8ff ingest(xpost): Brian Roemmele Amazon-Jailbreak Fable 5 als Auslöser der Exportkontrollen 2026-06-13 18:46:06 +02:00
Hector Bot
1c801c5a39 ingest(xpost): colgate-llm-purchase-intent-ssr 
- raw: raw/xpost/2026-06-11_colgate-llm-purchase-intent-ssr.md (created)
- wiki: wiki/concepts/semantic-similarity-rating-ssr.md (created)
- index: updated
- log: updated
 2026-06-12 10:38:30 +02:00
Hector the Butler
87e079fa45 chore: add raw/ and wiki/ directory skeletons with .gitkeep 2026-06-05 13:30:00 +02:00