https://codema.ai/articles/add-mcp-server-cursor-claude-code-codex.htmlCodemaen2026-10-21T00:00:00-04:00How to add an MCP server to Cursor, Claude Code and Codex https://codema.ai/articles/agent-skills-agentic-ai-foundation.htmlCodemaen2026-10-22T00:00:00-04:00Anthropic gives Agent Skills to the Agentic AI Foundation: what changes for your SKILL.md files https://codema.ai/articles/ai-bubble-capex-math.htmlCodemaen2026-10-22T00:00:00-04:00Is AI a bubble? Five numbers to check instead of guessing https://codema.ai/articles/ai-data-centres-power-grid-iea.htmlCodemaen2026-10-22T00:00:00-04:00AI data centres and the power grid: what the IEA numbers actually say https://codema.ai/articles/ai-financing-10-trillion-columbia-brookings.htmlCodemaen2026-10-22T00:00:00-04:00Who's paying for the $10 trillion AI build-out? A Columbia paper explains the plumbing https://codema.ai/articles/ai-impairment-explained-gartner.htmlCodemaen2026-10-22T00:00:00-04:00What's an impairment? Gartner's $3.5 trillion AI warning, explained https://codema.ai/articles/anthropic-confidential-ipo-filing.htmlCodemaen2026-10-22T00:00:00-04:00The Anthropic IPO, explained: what a confidential S-1 is and what's been reported https://codema.ai/articles/back-up-supabase-database.htmlCodemaen2026-10-21T00:00:00-04:00How to back up a Supabase database and export your data https://codema.ai/articles/big-tech-earnings-week-oct-2026-capex.htmlCodemaen2026-10-22T00:00:00-04:00Big Tech earnings week (Oct 28 to Nov 2): the dates and the AI-capex lines to read https://codema.ai/articles/china-draft-ai-export-controls.htmlCodemaen2026-10-22T00:00:00-04:00China's draft AI export controls: what they cover, what's exempt, and what it means for open models https://codema.ai/articles/chip-earnings-tsmc-lam-texas-instruments-q3-2026.htmlCodemaen2026-10-22T00:00:00-04:00Chip earnings, Q3 2026: what TSMC, Lam Research and Texas Instruments reported https://codema.ai/articles/claude-code-subagents-vs-skills-vs-hooks.htmlCodemaen2026-10-22T00:00:00-04:00Claude Code subagents vs skills vs hooks: which one to use, with examples https://codema.ai/articles/claude-duet-explained.htmlCodemaen2026-10-22T00:00:00-04:00Claude Duet, explained: Anthropic's proactive agent app, what it can do and who can get it https://codema.ai/articles/claude-opus-5-5-for-builders.htmlCodemaen2026-10-22T00:00:00-04:00Claude Opus 5.5 for builders: price, 1M context, and the four changes that break Opus 5 code https://codema.ai/articles/codex-cli-getting-started.htmlCodemaen2026-10-22T00:00:00-04:00Codex CLI from zero: install, sign in, /init and your first task https://codema.ai/articles/context-windows-explained.htmlCodemaen2026-10-22T00:00:00-04:00Context windows explained: tokens, 1M-token models and what actually fits https://codema.ai/articles/cost-to-rent-h100-b300-gpu.htmlCodemaen2026-10-22T00:00:00-04:00What it costs to rent an H100, H200, B200 or B300 in October 2026 https://codema.ai/articles/cxmt-china-memory-maker.htmlCodemaen2026-10-22T00:00:00-04:00Who is CXMT? China's DRAM maker, its giant IPO and the 4F² claim, explained https://codema.ai/articles/ddr5-buying-guide-late-2026.htmlCodemaen2026-10-22T00:00:00-04:00DDR5 buying guide for late 2026: how much to buy, what speed, and whether to wait https://codema.ai/articles/deepseek-v4-1-flash-deepinfer.htmlCodemaen2026-10-22T00:00:00-04:00DeepSeek open-sources DeepInfer: what V4.1 Flash is, and can you run it yourself? https://codema.ai/articles/design-md-design-system-for-coding-agents.htmlCodemaen2026-10-22T00:00:00-04:00DESIGN.md: give your coding agent a design system so every page looks the same https://codema.ai/articles/diffusion-llms-explained-mercury-3.htmlCodemaen2026-10-22T00:00:00-04:00Diffusion LLMs explained: what Mercury 3's 1,000 tokens per second means for builders https://codema.ai/articles/eps-beats-guidance-explained.htmlCodemaen2026-10-22T00:00:00-04:00EPS, beats and guidance, explained: how to read an earnings report in 5 minutes https://codema.ai/articles/flint-vs-ornith-local-coding-models.htmlCodemaen2026-10-22T00:00:00-04:00Flint vs Ornith 1.5: two new open coding models, and the hardware they actually need https://codema.ai/articles/flux-3-image-klein-8gb-gpu.htmlCodemaen2026-10-22T00:00:00-04:00FLUX 3 Image Klein: an open image model that runs on an 8GB GPU https://codema.ai/articles/ga4-predictive-audiences-google-ads.htmlCodemaen2026-10-21T00:00:00-04:00GA4 predictive audiences: how they work and how to use them in Google Ads https://codema.ai/articles/gddr7-vs-gddr6-vs-hbm.htmlCodemaen2026-10-22T00:00:00-04:00GDDR7 vs GDDR6 vs HBM: the memory inside GPUs, explained simply https://codema.ai/articles/gemini-4-argon-pricing-for-builders.htmlCodemaen2026-10-22T00:00:00-04:00Gemini 4 Argon for builders: pricing, caching, and when to pick it https://codema.ai/articles/gemini-api-cli-guide.htmlCodemaen2026-10-22T00:00:00-04:00gemini-api CLI: give Claude Code or Codex image, voice and video generation in 5 minutes https://codema.ai/articles/git-github-basics-for-vibe-coders.htmlCodemaen2026-10-21T00:00:00-04:00Git and GitHub basics for vibe coders: never lose AI-written code https://codema.ai/articles/gpt-6-explained-sol-luna-astra.htmlCodemaen2026-10-22T00:00:00-04:00GPT-6 explained: Sol vs Luna vs Astra, and what \"Intelligent UI\" means https://codema.ai/articles/gpu-backed-financing-spvs-explained.htmlCodemaen2026-10-22T00:00:00-04:00GPU-backed financing and SPVs, explained (plus Amazon's reported $8B chip deal) https://codema.ai/articles/h200-china-export-license-rule.htmlCodemaen2026-10-22T00:00:00-04:00The H200 China export rule, explained: what's allowed, the limits, and why NVIDIA still guides to zero https://codema.ai/articles/hbm-explained.htmlCodemaen2026-10-22T00:00:00-04:00HBM explained: the memory that decides how fast AI chips can think https://codema.ai/articles/hbm4-race-sk-hynix-samsung-micron.htmlCodemaen2026-10-22T00:00:00-04:00The HBM4 race: where SK hynix, Samsung and Micron stand in October 2026 https://codema.ai/articles/how-much-vram-for-local-llm.htmlCodemaen2026-10-22T00:00:00-04:00How much VRAM do you need to run an LLM locally? The simple math https://codema.ai/articles/how-to-read-a-10-q.htmlCodemaen2026-10-22T00:00:00-04:00How to read a 10-Q: a plain-English guide for tech investors https://codema.ai/articles/jetbrains-developers-delegate-ai-2026.htmlCodemaen2026-10-22T00:00:00-04:00Half of developers now let AI write their app logic: what JetBrains' 2026 survey found https://codema.ai/articles/kibitz-kalmia-arena-mystery-models.htmlCodemaen2026-10-22T00:00:00-04:00Mystery models on Arena: what we know about Kibitz and Kalmia, and how to read leaderboards https://codema.ai/articles/litellm-supply-chain-attack-what-to-do.htmlCodemaen2026-10-22T00:00:00-04:00LiteLLM 1.107.0 was compromised: how to check your machines and what to rotate https://codema.ai/articles/llm-api-pricing-compared-claude-gemini-minimax.htmlCodemaen2026-10-22T00:00:00-04:00LLM API pricing compared: Claude, Gemini, GPT-6, MiniMax and Mercury, side by side (Oct 2026) https://codema.ai/articles/mac-studio-m5-ultra-512gb-local-ai.htmlCodemaen2026-10-22T00:00:00-04:00Mac Studio M5 Ultra with 512GB: what it means for running big AI models at home https://codema.ai/articles/mcp-framer-mercury-what-agents-can-do.htmlCodemaen2026-10-22T00:00:00-04:00Framer MCP and Mercury MCP: what AI agents can now do in your website and bank account https://codema.ai/articles/mcp-security-best-practices.htmlCodemaen2026-10-21T00:00:00-04:00MCP security best practices: how to use MCP servers without leaking data https://codema.ai/articles/meta-q3-2026-earnings-capex.htmlCodemaen2026-10-22T00:00:00-04:00Meta's Q3 2026 earnings: revenue up 26%, free cash flow below zero https://codema.ai/articles/micron-nvidia-sp500-q3-earnings-growth.htmlCodemaen2026-10-22T00:00:00-04:00Two chip companies are carrying S&P 500 earnings growth in Q3 2026 https://codema.ai/articles/micron-record-fq4-2026-results.htmlCodemaen2026-10-22T00:00:00-04:00Micron's record fiscal Q4 2026: $54.2B revenue and an 87% gross margin https://codema.ai/articles/minimax-m3-1-flash.htmlCodemaen2026-10-22T00:00:00-04:00MiniMax M3.1 Flash: a 73.7% DeepSWE coding model at $0.15 per million tokens https://codema.ai/articles/neoclouds-coreweave-nebius-explained.htmlCodemaen2026-10-22T00:00:00-04:00Neoclouds explained: how CoreWeave and Nebius make (and spend) money https://codema.ai/articles/nokia-q3-2026-ai-cloud-growth.htmlCodemaen2026-10-22T00:00:00-04:00Nokia Q3 2026: AI and cloud sales more than doubled. Here's what that means https://codema.ai/articles/nvidia-dsx-pod-vera-rubin-ai-factories.htmlCodemaen2026-10-22T00:00:00-04:00NVIDIA DSX POD explained: AI factories in a container, from six months to 14 days https://codema.ai/articles/nvidia-nemotron-3-5-explained.htmlCodemaen2026-10-22T00:00:00-04:00NVIDIA Nemotron 3.5 explained: Super, Lightning and the Switchyard router https://codema.ai/articles/nvidia-q3-fy27-earnings-preview-data-center.htmlCodemaen2026-10-22T00:00:00-04:00NVIDIA Q3 FY2027 earnings preview: what $108 billion of guidance has to prove https://codema.ai/articles/ollama-for-beginners.htmlCodemaen2026-10-22T00:00:00-04:00Ollama for beginners: run your first local AI model in 5 minutes https://codema.ai/articles/opencode-console-breach-rotate-api-keys.htmlCodemaen2026-10-22T00:00:00-04:00The OpenCode Console breach: what happened, and how to rotate your API keys https://codema.ai/articles/opencode-local-llm-ollama-lm-studio-llama-cpp.htmlCodemaen2026-10-22T00:00:00-04:00Run OpenCode on a local model: Ollama, LM Studio and llama.cpp configs that work https://codema.ai/articles/perplexity-computer-local-mac.htmlCodemaen2026-10-22T00:00:00-04:00Perplexity Computer now runs fully locally on Mac: what you need and what stays private https://codema.ai/articles/prompt-caching-explained.htmlCodemaen2026-10-22T00:00:00-04:00Prompt caching explained: how to cut your AI API bill without changing models https://codema.ai/articles/ps6-memory-crunch-console-prices.htmlCodemaen2026-10-22T00:00:00-04:00PS6 and the memory crunch: why AI demand could push next-gen console prices up https://codema.ai/articles/rtx-5090-price-gddr7-shortage.htmlCodemaen2026-10-22T00:00:00-04:00Why the RTX 5090 costs several times its $1,999 launch price right now https://codema.ai/articles/rtx-spark-laptops-128gb-unified-memory.htmlCodemaen2026-10-22T00:00:00-04:00NVIDIA RTX Spark laptops: 128GB of unified memory on Windows, explained https://codema.ai/articles/run-coding-agents-safely-permissions-sandboxes.htmlCodemaen2026-10-21T00:00:00-04:00How to run coding agents safely: permissions, sandboxes and secrets https://codema.ai/articles/run-model-bigger-than-ram-mmap-offload.htmlCodemaen2026-10-22T00:00:00-04:00Can you run an AI model bigger than your RAM? mmap and offloading, explained https://codema.ai/articles/sk-hynix-q3-2026-earnings-preview.htmlCodemaen2026-10-22T00:00:00-04:00SK hynix Q3 2026 earnings preview: the date, the record Q2 and what to watch https://codema.ai/articles/ssd-nand-prices-q4-2026.htmlCodemaen2026-10-22T00:00:00-04:00SSD and NAND prices in Q4 2026: why AI is now eating storage too https://codema.ai/articles/t3-code-guide.htmlCodemaen2026-10-22T00:00:00-04:00T3 Code: one app to run Claude Code, Codex, Cursor and OpenCode, including from your phone https://codema.ai/articles/tesla-q3-2026-earnings.htmlCodemaen2026-10-22T00:00:00-04:00Tesla's Q3 2026 earnings: flat revenue, thinner margins, bigger capex https://codema.ai/articles/tpu-vs-gpu-explained.htmlCodemaen2026-10-22T00:00:00-04:00TPU vs GPU: what's the difference, and which one runs your AI? https://codema.ai/articles/unified-memory-mac-studio-vs-rtx-spark-vs-gpu.htmlCodemaen2026-10-22T00:00:00-04:00Unified memory explained: Mac Studio vs RTX Spark vs a desktop GPU for local AI https://codema.ai/articles/utm-tracking-setup-guide.htmlCodemaen2026-10-21T00:00:00-04:00UTM tracking setup: a UTM naming guide for AI-built sites https://codema.ai/articles/vllm-openai-compatible-server-guide.htmlCodemaen2026-10-22T00:00:00-04:00How to run vLLM as an OpenAI-compatible server (and swap it into your app) https://codema.ai/articles/what-2nm-means-tsmc-n2-gaa.htmlCodemaen2026-10-22T00:00:00-04:00What does '2nm' actually mean? TSMC N2 and nanosheet transistors, explained https://codema.ai/articles/what-is-agents-md-how-to-write-one.htmlCodemaen2026-10-21T00:00:00-04:00What is AGENTS.md? How to write one your coding agents follow https://codema.ai/articles/what-is-an-agent-harness-harness2.htmlCodemaen2026-10-22T00:00:00-04:00What is an agent harness? Google's Harness² shows why it matters as much as the model https://codema.ai/articles/whats-inside-smh-semiconductor-etf.htmlCodemaen2026-10-22T00:00:00-04:00What's inside a semiconductor ETF? How SMH's index picks and weights its 25 chip stocks https://codema.ai/articles/why-is-ram-so-expensive-2026.htmlCodemaen2026-10-22T00:00:00-04:00Why is RAM so expensive right now, and when will prices come down?