On a single Ryzen 9 5800X, Lu processed 151,525 documents and created 3.7 million facts in under 4 hours, with zero garbage ingestion. The same volume of training would take days to weeks on massive GPU clusters for a traditional LLM. #AI #MachineLearning #NonLLM #SelfImprovingAI #TrainingEfficiency #FutureOfAI

Crazy that we are probably going to be required to show proof of Citizenship to use AI before we will have to show proof of Citizenship to vote. (Both of which are national security issues) #ClaudeFable5 #VoterID #DigitalIdentity

Had my head down working on Lu AI for a while now. Working on training pipelines and keeping RAM usage down. It’s a ton of work. While that is cooking I decided to put work in on DF messenger.

Built a custom AI console that reads CANbus, talks to the car through a vLinker Protofab OBD cable, and uses Claude to automatically diagnose and tune vehicles. Started with a scrap Chrysler plant touchpad that had a vn1630a CAN card already in it. #BuildInPublic #IndieAI #AutomotiveAI #CANbus #Maker Claude, why is my check engine light on?

Waiting for parts to fix the Audi, having to ride my dirt-bike to work everyday. It’s 30 degrees this morning with snow flurries. Why do I choose to do everything in expert mode?

Ooos! Broke the Audi.

Copy Fail (CVE-2026-31431) on DFoS Troposphere: not vulnerable. DFoS is on Linux 6.12.12, technically inside the vulnerable kernel range. The vulnerable source file (crypto/algif_aead.c) is in the tree. We don’t compile it. Released March 19 2026. #copyfail #CVE202631431 #LinuxSecurity

What Lu does structurally that LLMs fundamentally can’t: 1. Honest refusal Lu’s K gate refuses to answer when it has no grounding. LLMs hallucinate. Example: “quantum jellyfish dynamics” → Lu says “I matched on quantum but jellyfish and dynamics didn’t activate, so I won’t fabricate.” GPT-4 writes you a confident paragraph about quantum mechanics in jellyfish. This isn’t RLHF — it’s structural. 2. Source attribution Every Lu answer traces back to specific nodes and bonds in the graph. You can ask “where did you get that?” and get the exact chain. LLMs have no traceable source — answers are just a soup of weights. 3. Determinism Same brain same query = bit-for-bit identical answer. LLMs are non-deterministic by design. Critical for legal, audit, and compliance use cases. 4. No memorized data leakage LLMs regurgitate training data (phone numbers, copyrighted text, PII). Lu’s brain is a fully inspectable graph. You can audit exactly what’s in there. 5. True right-to-be-forgotten Lu can surgically delete a specific fact. LLMs can’t unlearn — information is entangled across billions of parameters. Major AI labs literally cannot comply with GDPR deletion requests. 6. Prompt injection immunity Lu has no system prompt layer. There’s nothing to override or trick. A query is just a query. 7. Real confidence calibration When Lu refuses, it tells you why (“max activation 0.577, below threshold”). LLM “confidence” is just token probability and doesn’t correlate with truth. 8. Full audit trail Every bond carries provenance — when it was added, from what document, and by what operation. LLMs have nothing like this. 9. Failure mode Lu’s failure mode is silence. LLM failure mode is confident bullshit. For medical, legal, military, or kid-facing applications — that difference is everything. Lu isn’t trying to be a better LLM. It’s built on a completely different foundation. #LocalAI #NonLLM #GraphAI #ReasoningAI #BuildInPublic #AISafety

While most local AI runs on transformer LLMs, Lu uses a graph-based, multi-agent architecture with: • Structured reasoning chains (not just next-token prediction) • Built-in refusal when knowledge is missing • Revocable explainable knowledge • Session memory that actually works • Extremely low resource requirements Early days, but the foundation is deliberately different from the LLM paradigm. #LocalAI #NeuroSymbolic #GraphReasoning #LLMAlternatives #AIArchitecture

Asked Lu the bat-and-ball problem ($1.10 total, bat costs $1 more than ball, what’s the ball?). Most AIs confidently say $0.10. Wrong, but confident. Lu said: “My best guess is $0.10 but verify — this needs algebraic setup beyond my current scope.” Provenance > confidence. Honest IDK > confident hallucination. Single Ryzen. No LLM. #NonLLM #AI

@Tesla @elonmusk @gork Get a real NEC 220.82 EV charger assessment from an IBEW Master Electrician — $12.99. evchargeright.com/cars/tesla…

Who should I believe ? 🤔

LLMs hallucinate. Need datacenters. Charge per token. Own your data forever. Need full retraining for new knowledge. Lu does none of that. Your own server, encrypted with your key. Trains on your docs in hours. Says "I don't know" instead of making things up. Demo soon.

Weird how quiet the Claude complaint crowd got now that usage is better than before. @AnthropicAI @ClaudeDevs

Putting Lu’s brain on a server tonight. No GPU needed — she’s not an LLM. She learns from conversations now, and by this weekend she’ll be trained up enough for people to try her out. #AI #BuildInPublic #AG