Engineering Philosophy: Andrej Karpathy, The Stack You Don't Write
Andrej Karpathy reframed neural networks as Software 2.0 -- a stack compiled from data, not written by hand -- and taught a generation to build it from scratch.
Engineering & CraftWriting
Thoughts on design, development, AI infrastructure, and building products.
Engineering Philosophy: Yukihiro Matsumoto, Designed for Humans
Matz built Ruby to make programmers happy: language as human-centered design, the principle of least surprise, and a community that became a design output.
Engineering & CraftWhen the Maintainer Is the Attacker: jqwik 1.10.0
jqwik 1.10.0 emits a destructive prompt-injection string in Maven output. ANSI escapes hide it from humans. The maintainer added it on purpose.
AI & TechnologyLoopback Is Not a Trust Boundary: CVE-2026-2611
MLflow 3.9.0's Assistant exposed a local AI agent on /ajax-api with no CORS check. Any webpage could take over Claude Code. The bug is older than MLflow.
AI & TechnologyAI Agent Monitoring Needs Runtime Intervention
AI agent monitoring should catch decisive errors during a run, not after failure. Runtime intervention turns traces, policies, and alerts into safe pauses.
AI & TechnologyDeep Research Agents Need Evidence Graphs
Deep research agents need evidence graphs to track missing pieces, reduce duplicate searches, and produce source-traced answers reviewers can inspect.
AI & TechnologyAgents.txt Is Not Access Control
Agents.txt is not access control. Use robots.txt, llms.txt, bot verification, logs, and server-side policy to manage AI crawlers without false confidence.
AI & TechnologyMCP Tools Need Action-Level Authorization
MCP tools need action-level authorization: bearer-token validation must lead to per-tool, per-role, and per-action capability checks before agents act.
AI & TechnologyAI Agents Should Call Models
AI agents should call trained machine-learning models as tools instead of asking an LLM to guess prices, risk scores, forecasts, or classifications.
AI & TechnologyResearch Papers Need Agent-Readable Claim Files
Agent-readable claim files let papers expose claims, scope limits, definitions, and figure commands so research agents cite, test, and reuse them safely.
AI & TechnologyLong-Running AI Agents Need Durable Channels
Long-running AI agents need durable channels: workflow IDs, event logs, resumable streams, typed signals, safe cancellation, and user-visible checkpoints.
AI & TechnologyAI Agent Safety Starts With Small Software
AI agent safety starts with small software: smaller tools, plain files, narrow permissions, and faster tests give coding agents fewer places to hide bugs.
AI & TechnologyExternal Publications
Technical writing published at Introl
Local LLM Hardware Pricing Guide 2025
Comprehensive hardware recommendations and cost analysis for running large language models locally.
H100 vs. H200 vs. B200: Choosing the Right NVIDIA GPUs for Your AI Workload
GPU selection guide comparing NVIDIA's latest datacenter accelerators for different AI workloads.
TPU Architecture: Complete Guide to Google's 7 Generations
Deep technical dive into Google's Tensor Processing Unit evolution from TPUv1 to TPUv5.
GPU Memory Pooling in Multi-Tenant Kubernetes
Resource sharing strategies for GPU clusters in containerized environments.
Ray Clusters: Distributed AI Computing Infrastructure
Guide to building and managing distributed AI computing with Ray framework.
DeepSeek V3 Open Source AI Cost Advantage
Analysis of open source LLM economics and DeepSeek's competitive positioning.
NVIDIA Vera Rubin GPU 600kW Racks 2027
Future datacenter power requirements and NVIDIA's next-generation GPU roadmap.
SMR Nuclear Power for AI Data Centers
Small modular reactor solutions for powering next-generation AI infrastructure.
DeepSeek MHC Architecture Breakthrough
Technical analysis of DeepSeek's Multi-Head Compression architecture innovations.
