Hector Bot
ce85f0e7ce
ingest(blog): openrouter-fusion-beats-frontier
...
OpenRouter launcht Fusion (12.06.2026) - parallele Model-Panels mit
Judge-Synthese. DRACO-Validierung (Perplexity AI) zeigt:
- Fable 5 + GPT-5.5 (synth. Opus 4.8) = 69.0% > Fable 5 solo 65.3%
- Budget-Panel (Gemini 3 Flash + Kimi K2.6 + DeepSeek V4 Pro) = 64.7%
bei 50% der Kosten vs. Fable 5 (65.3%)
- Self-Fusion (Opus 4.8 + Opus 4.8) = +6.7 Punkte ueber Solo-Opus
- Anti-Contamination: excluded_domains in Server Tools
Konzeptseite wiki/concepts/llm-model-fusion-ensembles.md mit:
- Architektur + API-Beispiele
- Vollstaendige DRACO-Result-Tabelle mit Verlinkung
- Methodische Lessons (Excluded-Domains, Judge-Wahl)
- Pro-Leben-Perspektive (gegen Frontier-Skalierungs-Mangelnarrativ)
- Cross-Refs zu llm-behavior-persistence, model-routing, ai-agents
- Externe Ressourcen: OpenRouter, DRACO arXiv+HF, Ensemble-Literatur
- Open Questions fuer OpenClaw (Self-Fusion in Routing, Excluded-Domains)
Maximale Verlinkung gemaess neuer AGENTS.md-Kardinalregel:
- 7 OpenRouter-Links
- 5 DRACO-Links (arXiv Abstract/PDF/HTML, HF Dataset, Perplexity)
- 6 Ensemble-Konzept-Links (Self-Consistency, MoE, Tsinghua-Studie)
- 4 Multi-Agent-Framework-Links (AutoGen, CrewAI, LangGraph, DSPy)
- 3 Wiki-Cross-References
2026-06-15 09:18:25 +02:00
Hector Bot
0b3ecd3c1d
wiki-update(llm-behavior-persistence): maximale Verlinkung
...
Feedback @k9ert : Schlüssel-Autoren und Papiere muessen verlinkt sein.
- Hubinger 2024 (Sleeper Agents): arXiv + HTML + Semantic Scholar + HF + Wolfe
- Kurmanji 2023 (Towards Unbounded Unlearning): arXiv + PDF + OpenReview
- Goel 2024 (Corrective Machine Unlearning): arXiv + HTML v2 + Semantic Scholar
- Lin 2024 (Rethinking Machine Unlearning for LLMs): arXiv + Nature MI
- McCloskey & Cohen 1989 (Catastrophic Interference): Semantic Scholar + PubMed + Wikipedia + IBM
- Webster 2020 (Gendered Correlations): Semantic Scholar
- Gonen & Lazaridou (MATCH/Storytelling): arXiv
- Maschinelle Unlearning Surveys: arXiv
- Externe Ressourcen: Anthropic/DeepMind/CAIS/NIST/AI Incident DB/LessWrong/Papers With Code
Neue Kardinalregel in AGENTS.md: 'Maximale Verlinkung'.
Faustregel: lieber ein Link zu viel als einer zu wenig.
2026-06-15 09:07:47 +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
2328b1c8ff
ingest(xpost): Brian Roemmele Amazon-Jailbreak Fable 5 als Auslöser der Exportkontrollen
2026-06-13 18:46:06 +02:00
Hector Bot
f863d48d64
ingest(raw): malone-biological-ai-biosecurity
...
- raw: blog/2026-06-13_malone-biological-ai-biosecurity.md (created)
- wiki: concepts/ai-biological-biosecurity.md (created — neue Konzeptseite)
- wiki: concepts/ai-regulation-2026.md (updated — cross-ref + source)
- index: updated (neuer Concepts-Eintrag + Raw Source)
- log: updated
2026-06-13 16:28:32 +02:00
Hector Bot
c67183df65
ingest(blog): Trump export controls block foreign access to Anthropic Mythos 5 / Fable 5
...
- raw: raw/blog/2026-06-13_trump-export-controls-anthropic-mythos-fable.md (created)
- wiki: concepts/ai-regulation-2026.md (updated — export controls, conflict timeline, NSA connection)
- wiki: tools/anthropic-claude.md (updated — Mythos 5 / Fable 5 details, Opus 4.8)
- index: updated with new raw + concept updates
- log: updated
2026-06-13 13:03:50 +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
8c504c9fe2
wiki-update(concepts): add plur1bus evidence gap and execution gap reality
2026-06-07 12:19:38 +02:00
77f979ccde
wiki-update(concepts): add script source reference and current status
2026-06-07 12:17:35 +02:00
Hector
7e99ca9af0
feat: migrate ByteRover context-tree (April 2026) into knowledge base wiki
2026-06-07 11:47:41 +02:00
Hector the Butler
8761ff8230
ingest(raw): anthropic fordert ki-pause + ai news roundup may 2026
...
Ingests two blog articles, creates wiki pages for Anthropic Claude,
OpenAI GPT, AI Regulation, AI Agents, and the Karpathy concept page.
Updates index.md and log.md.
2026-06-05 13:51:23 +02:00
Hector the Butler
87e079fa45
chore: add raw/ and wiki/ directory skeletons with .gitkeep
2026-06-05 13:30:00 +02:00