Articles
CPU Inference -- ongoing series
herbert-rs -- local LLM inference engine in Rust
PriorityQueue in Rust -- video series
Step-by-step implementation of a priority queue in Rust
All Articles
2026
- 2026-03-15 - CPU Inference #0: understand before optimizing
- 2026-02-20 - CPU Inference #1: The three regimes
- 2026-02-17 - Qwen3 vs Qwen3.5: What Actually Changes
- 2026-02-13 - From gpt2-experiments to qwen3-experiments-rs: The Memory Wall
- 2026-02-07 - Tile-major layout and transformer memory allocations
- 2026-02-05 - OPNI: when the Vibe Coder forgets the Stop button
- 2026-01-30 - Generative AI and Software Liability: What Changes in 2026
- 2026-01-20 - Beating PyTorch with Rust and 180 Lines of Assembly
- 2026-01-15 - How tech is losing its craft
2025
- 2025-11-16 - ▶ PriorityQueue - Rust #006 - async/await
- 2025-11-09 - ▶ PriorityQueue - Rust #005 - Graceful Shutdown
- 2025-11-02 - ▶ PriorityQueue - Rust #004 - Blocking Dequeue
- 2025-11-02 - Cursor and Windsurf Run on Chinese AI Models
- 2025-10-26 - ▶ PriorityQueue - Rust #003 - Multithreading
- 2025-10-17 - ▶ PriorityQueue - Rust #002 - Fairness
- 2025-10-10 - ▶ PriorityQueue - Rust #001
- 2025-08-24 - Test Your Rust Knowledge
- 2025-08-23 - Deep Dive into Safe Concurrency with Rust
- 2025-08-22 - Rust and Miri: Beyond the Compiler for Memory Safety
- 2025-08-17 - ▶ Real Costs of Matrix Multiplication (Unoptimized)
- 2025-08-15 - Virtual Memory, TLBs and NX Bit Simulation: A Journey into x86 32-bit
- 2025-08-14 - Tenstorrent and Float Multiplication, and Why SLMs Are the Future
- 2025-08-13 - Active Testing: Testing LLMs the Smart Way
- 2025-08-10 - Qwen3 vs GPT-OSS: CPU Benchmark Without GPU
- 2025-08-09 - MXFP4: Revolution or Evolution?
- 2025-08-09 - Plan 9: An Operating System That Shaped My Career
- 2025-08-08 - Why AI Slows Down as the Conversation Grows
- 2025-08-05 - Business Debt: When Teams Shape Systems That Last
- 2025-08-04 - KV Cache Optimization in LLMs
- 2025-08-02 - Towards Energy-Efficient Conversational AI
- 2025-08-01 - RAG: AI Without Hallucinations
- 2025-07-31 - Kafka, Pulsar or Ray? A Comparison for Distributed AI
- 2025-07-30 - Three-Body System: Thinking Distributed AI with Rust
- 2025-07-29 - Why I Designed My Own LLM Orchestrator in Rust
- 2025-07-28 - The Case for Sovereign and Frugal AI
- 2025-07-25 - America Accelerates on AI: What About France?
- 2025-07-25 - Why LLMs Sometimes Get Stuck in Loops
2019
- 2019-06-11 - Go MySQL Tutorial [Part 2: Connection and Configuration]
- 2019-06-11 - Go MySQL Tutorial [Part 3: Data Transfer]
- 2019-06-11 - Go MySQL Tutorial [Part 1: Installation]
- 2019-06-11 - Go MySQL Tutorial [Part 4: Transactions]
- 2019-06-10 - Dive into Go API
- 2019-02-28 - Cloud Act, Patriot Act, GDPR
- 2019-01-15 - My readings: Space Opera
2018
- 2018-10-21 - Sequence Models course certificate on Coursera
- 2018-08-25 - Blogging with Hugo website generator
- 2018-05-24 - 'Neural Networks and Deep Learning' or why I like KISS
2015
- 2015-11-25 - 100 Years of General Relativity
- 2015-04-01 - Plan9 Operating System