NanoKnow: How to Know What Your Language Model Knows
Paper
• 2602.20122 • Published
• 4
Stefan Schweter PRO
stefan-it
AI & ML interests
Flair Library 💕, NER & PoS Tagging, LM Pretraining (mostly encoder-only & encoder-decoder), Historical Language Models, German Language Models, Bavarian NLP 🥨
Recent Activity
liked
a dataset 4 days ago
windprak/steuerllm_instruct_dataset reacted
to
SeaWolf-AI's
post with 🔥 4 days ago
Do Bubbles Form When Tens of Thousands of AIs Simulate Capitalism?
We gave LLMs autonomous trading over 30 real tickers at 100x leverage. All went bankrupt in 30 minutes from hallucination. This spawned FINAL Bench (first metacognition benchmark) and AI NPC Trading Arena — tens of thousands of metacognition-equipped AI agents competing under capitalist rules. Humans can only watch.
Live Demo: https://huggingface.co/spaces/Heartsync/Prompt-Dump
Article: https://huggingface.co/blog/FINAL-Bench/pumpdump
NPCs form a society: 3-tier memory, self-modifying parameters, mutual criticism, strategy propagation, and a virtual SEC enforcing fines every 20 minutes. Every trade passes 4-stage verification including Brave Search fact-check. FINAL Bench confirmed across 9 SOTA models that AI can say "I might be wrong" (MA 0.694) but cannot actually fix errors (ER 0.302).
Six findings: Bubbles form naturally through knowledge transfer and swarm herding. Identical NPCs diverge irreversibly from their first three trades. Metacognition blocks individual hallucination but not collective herding — this is the key finding. Information asymmetry solidifies hierarchy. Fraud and regulation co-evolve. Criticism improves returns.
Individual intelligence does not guarantee collective intelligence.
Dataset & Paper:
https://huggingface.co/datasets/FINAL-Bench/Metacognitive liked
a dataset 4 days ago
castorini/NanoKnow-Fineweb-Edu-Index Organizations
upvoted a paper 4 days ago
upvoted an article 4 days ago
Article
Do Bubbles Form When Tens of Thousands of AIs Simulate Capitalism?
•
17
upvoted a paper 5 days ago
upvoted a collection 11 days ago
upvoted 2 papers 11 days ago
upvoted a collection 11 days ago
upvoted 3 papers 17 days ago
LoRA-Squeeze: Simple and Effective Post-Tuning and In-Tuning Compression of LoRA Modules
Paper
• 2602.10993 • Published
• 1
Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning
Paper
• 2602.11149 • Published
• 14
SteuerLLM: Local specialized large language model for German tax law analysis
Paper
• 2602.11081 • Published
• 1
upvoted a collection 18 days ago
upvoted a paper 20 days ago
upvoted a collection 25 days ago
upvoted a paper about 1 month ago
upvoted a collection about 1 month ago
upvoted 2 papers about 1 month ago
upvoted an article about 1 month ago
Article
How We Built a Semantic Highlight Model To Save Token Cost for RAG
•
65
upvoted a collection about 1 month ago
upvoted a paper about 2 months ago