Block or report maxbaluev
Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.
You must be logged in to block users.
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseMost AI forgets. I build the kind that remembers what worked — and ships the code that proves it.
Founding / Staff AI engineer. I build self-improving AI systems on the hard primitives — late-interaction retrieval, agent memory, and reinforcement-style credit assignment — and ship the code that proves them.
Most AI forgets: a model scores 90% today and 90% tomorrow; what worked, what failed, what to avoid is generated and thrown away. I work on the opposite — systems whose judgment compounds from reality, getting sharper with use because outcomes are scored and bound to the next decision. That thesis is Accreted Intelligence.
| Repo | What it proves |
|---|---|
| accreted-intelligence | The thesis + whitepaper: a Recursive Language Model over late-interaction scored-token memory, where the model is a replaceable processor and judgment lives in scored state. |
| maxsim-rs | ColBERT-style late-interaction MaxSim, in clean zero-dependency Rust — the retrieval primitive, done right. |
| colpali-retrieve | Multimodal late interaction — a text query retrieves over document-page images by patch-level MaxSim (ColPali-style). |
| scored-rerank | Ranking that learns from outcomes — Beta-Bernoulli posteriors + Thompson sampling rank by what reality confirmed, not just base similarity. |
| mcp-retrieve | An MCP server exposing late-interaction retrieval as an agent tool — retrieval where agents actually consume it. |
Core: late interaction (ColBERT · ColPali · MaxSim) · Recursive Language Models · RL credit assignment · agent memory · retrieval / RAG systems
Tools: Rust · Python · MCP · DSPy · PyTorch · SQLite · browser automation
| Self-improving agent memory: late-interaction retrieval + outcome-credited posteriors, an owner-authority floor, and two reasoners over one substrate. | Real-time emotional text-to-speech. Led the AI + systems from zero. |
| Chat-based AI automating website / CRM / ads for SMBs (DSPy + MCP). | Peer-to-peer WebRTC CDN — distributed delivery at the edge. |
Exploring Staff / Principal / Founding AI Engineer roles — remote from GMT−3, full US/EU-hours overlap, contractor-ready — in retrieval, agent memory, and RL-for-LLMs. CV on request.
"Reasoning is getting cheaper. Judgment is not. I build for the part that compounds."
Pinned Loading
If the problem persists, check the GitHub status page or contact support.