Hi, I’m Viktor.I wasn’t a programmer. I didn’t build apps. I didn’t write code.My path here was... different.I was born in Russia, but moved to South Korea at 20, forced by political circumstances. For four years, I worked in greenhouses, on construction sites, in factories — I even dismantled mattresses for a living.Later, I crossed the border from Mexico into the U.S. and applied for asylum....
I just pushed the current SOTA on the LoCoMo long-term memory benchmark for agents: 80.1 % accuracy using only: -BGE-large-en-v1.5 (1024d) + FAISS-Custom “MCA” gravitational ranking (keyword coverage + importance + frequency)-BM25 sparse retrieval-Direct Cross-Encoder reranking (bge-reranker-v2-m3) on the full union (~120-150 docs)-Gpt-4o-mini only for final answer generation and judging...
I’ve been experimenting with long-term memory architectures for agent systems and wanted to share some technical results that might be useful to others working on retrieval pipelines. Benchmark: LoCoMo (10 runs × 10 conversation sets) Average accuracy: 80.1% Setup: full isolation across all 10 conv groups (no cross-contamination, no shared memory between runs)Architecture (all open weights...
I Learned AI from scratch - and discovered why current LLM hype misses the point. In this piece I walk through what building an AI memory system taught me about why coding skills remain essential, and what future programmers need instead of “AI replacing coding.I tried to make this article as engaging as possible to share my journey, and I’d really appreciate your feedback:...
Love what you're doing with ChatIndex - the hierarchical tree approach is really smart! Preserving all raw data
while adding semantic navigation layers is an elegant solution. We're solving similar problems from different
angles (you: lossless trees, me: gravitational ranking).
Starred your repo! Looking forward to seeing benchmarks when you release them. Keep building!I’ve been experimenting with long-term memory architectures for agent systems and wanted to share some technical results that might be useful to others working on retrieval pipelines.Benchmark: LoCoMo (10 runs × 10 conversation sets) Average accuracy: 80.1% Setup: full isolation across all 10 conv groups (no cross-contamination, no shared memory between runs)Architecture (all open weights...
I just pushed the current SOTA on the LoCoMo long-term memory benchmark for agents: 80.1 % accuracy using only:-BGE-large-en-v1.5 (1024d) + FAISS-Custom “MCA” gravitational ranking (keyword coverage + importance + frequency)-BM25 sparse retrieval-Direct Cross-Encoder reranking (bge-reranker-v2-m3) on the full union (~120-150 docs)-Gpt-4o-mini only for final answer generation and judging...
https://github.com/vac-architector/VAC-Memory-System
I’ve been working on an independent memory-retrieval architecture for agent systems. I don’t have a CS background — previously worked climbing cell towers and doing handyman jobs — but I spent the last 4.5 months building a hybrid memory system from scratch.The system combines FAISS, BM25, and a symbolic ranking layer (MCA). Answers are generated with GPT-4o-mini at temperature 0. The focus is...