Learn AI by Building
From your first dataset to production agents — deep-dive series, hands-on notebooks, and experiments you can rerun yourself.
Tutorials
View All →LLM Agent Cookbook
Build AI agents from scratch — ReAct, Tool Use, Multi-Agent orchestration
ML Cookbook
Master machine learning algorithms with hands-on Jupyter projects
Data Analysis Cookbook
SQL, Pandas, Statistics — everything for data-driven decisions
Ontology & KG Cookbook
RDF, OWL, Neo4j, and GraphRAG for knowledge-powered AI
Paper of the Week
All Issues →Paper of the Week #1 — Sparse Is Not the Same as Interpretable
I trained BDH and counted more than 4.8 billion activations across three controls. Training moved its single-latent sparsity from 49.98% to 81.65%, but a similar-budget ReLU baseline reached 91.04%. Sparsity is real; by itself, it is not evidence of interpretability.
Premium Series
Our Products
Tools we built for developers and job seekers
DrillCheck
AI-powered mock interviews — practice with real questions and get instant feedback
VibeCheck
Vibe-check your project — get AI feedback on your side project ideas
SpecRadar
Find what to build next — discover gaps in existing products and market opportunities
SpecRadar Career
Hottest tech skills from job posts — newsletter and CV analysis for your career
Starter Kits
View All →Practice notebooks, interview questions, and project solutions — ready to download.
Browse Starter KitsLatest Posts
View All →
TurboQuant in vLLM on One A100 — Capacity, Speed, and Accuracy of All Four Presets on an 8B Model
vLLM 0.28, Qwen3-8B bf16, one A100 80GB: KV capacity, batched throughput, 32K decode, needle-in-haystack, and GSM8K for bf16, fp8, and all four TurboQuant presets — the 8B size vLLM's own study skipped.
Hybrid Mamba-Transformer, Measured — Qwen3.5-9B Fits 4.4x More Context and 3.6x More Requests on the Same A100
Cache memory of Qwen3.5-9B (24 linear + 8 attention layers) vs Qwen3-8B measured from 2K to 64K context on one A100: 4.4x smaller at 64K, +37% prefill and 3.6x concurrency in vLLM — Part 1's claims confirmed, with a guide to which measurements can legitimately show it.
TurboQuant From Scratch on Real KV Tensors — What 3 Bits Actually Cost, and Why the Forks Beat the Paper's Layout
PolarQuant in 60 lines of PyTorch on real KV from Llama-3.2-1B and Qwen3-8B: 3-bit costs +10% perplexity, k8v4 +0.2%, QJL only pays below 4 bits, and the block-32 layout explains half the forks' edge.
TurboQuant llama.cpp CUDA Fork, Measured on an A100 — turbo4 Matches q4_0, turbo3 Breaks at Long Context
Qwen3-8B Q4_K_M on one A100, six KV types: perplexity, prefill, decode-at-depth, and VRAM measured. turbo4 matches q4_0 quality and beats q8_0 decode 2.5x at depth; turbo3 triples perplexity at 32K context.
TurboQuant Status Check, August 2026 — What Actually Shipped in vLLM, llama.cpp, and Ollama
vLLM shipped it in v0.20 and published a sobering benchmark; llama.cpp upstream rejected it in June; Ollama's implementation is dead. We also correct our own earlier "merged in llama.cpp" claim — with links.
CLAUDE.md Templates for Five Project Types — Copy, Paste, and the Rules That Actually Change Agent Behavior
Five CLAUDE.md/AGENTS.md templates — Next.js, Python ML, monorepo, data pipeline, research notebook — plus which lines agents actually obey and how to use a rules file to govern side effects.