Insights for AI builders
Tutorials, product updates, and ideas to help you build and ship AI applications faster.
Subscribe via RSS
How to Build a Personal AI Database for Finances, Health, and Email
A guide to building a personal "control tower" app with an AI agent and a Supabase database to track finances, health, and email in one place.
Anthropic's IPO Filing: Who Gets Rich and What It Reveals
Anthropic's S1 filing shows billions in revenue and losses, plus a path to nine-figure payouts for hundreds of employees at IPO.
ChatGPT Doubled Usage Limits on Its $100 and $500 Plans
OpenAI doubled usage limits on its $100 and $500 ChatGPT plans instead of cutting them, leaving the $20 tier feeling increasingly squeezed.
ChatGPT's Dots Assistant Adds Phone, Call, and iCloud Features
ChatGPT's proactive dots assistant now links to phone messaging, makes faster calls, and connects iCloud mail and calendar. Here's what changed.
Claude Duet Explained: Anthropic's Proactive Agent App and Waitlist
Claude Duet scans email and calendar, drafts replies, and asks before acting. Here's how Anthropic's new agent app works and who can try it.
Claude Haiku vs Sonnet vs Opus vs Fable: Which Model to Use
A practical comparison of Claude's model lineup, Haiku, Sonnet, Opus, and Fable, covering speed, cost, and when to use each one.
Claude Pricing Explained: Free, Pro, Max, and Ultra Plans Compared
Claude's free, Pro, Max, and Ultra plans explained: weekly limits, session caps, API credits, and which tier actually fits your workflow.
DeepSeek Stack: Install Guide to Make DeepSeek V4.1 Flash Code Like Opus
How to install DeepSeek Stack, a free 29-skill pack that pushes DeepSeek V4.1 Flash closer to Claude Opus level coding, step by step.
What Happens When Everyone Can Build Software With AI
AI coding agents are letting non-engineers ship real apps. Here's how the shift is playing out, based on YC's Lightcone and Supabase's own numbers.
Genie 4 Access: How to Try Google's World Model and What It Costs
Genie 4 is in limited research preview and rolling out to Google AI Ultra's $250/month plan. Here's who gets access and when.
GPT 6.1 Terra vs Claude Opus 5.5: Which Wins on Real Coding Tasks?
Hands-on tests pit GPT 6.1 Terra against Claude Opus 5.5 on coding, design, and game-building to see which actually delivers more for less.
GPT 6.1 Terra Pricing Explained: How It Stacks Up vs Soul and Astra
GPT 6.1 Terra's pricing sits below Soul and Astra, but is it actually cheaper per task? Here's the real cost breakdown across effort modes.
How to Set Up Grokbot: Building an AI Workforce Step by Step
A practical guide to setting up Grokbot bots, assigning a chief of staff, connecting apps, and automating recurring work from scratch.
Grokbot's AI Hedge Fund: Can Bot Analysts Beat the S&P 500?
A demo builds an AI "hedge fund" of Grokbot agents (analysts, clerks, traders) to paper-trade stocks against the S&P 500. Here's how it works.
Grokbot's New Features: Pages, Slides, Phone Apps, and Routines Explained
Grokbot added Notion-style pages, Google Slides-style output, phone app connections, and password manager integration. Here's what each feature does.
How to Use Claude Code Skills to Automate Repeated Tasks
Learn how Claude Code skills, memory, and the CLAUDE.md file help automate recurring workflows without writing scripts or code.
HP ZGX Fury Review: A Shared AI Workstation, Not a Desktop GPU
HP's ZGX Fury pairs Nvidia's GB300 Blackwell Ultra chip with 748GB unified memory to serve large open models to an entire team on-prem.
Kimi K3.1 Pro: Moonshot AI's Open-Weight Model Challenges Opus and Astra
Kimi K3.1 Pro is a 2.8T parameter open-weight model from Moonshot AI with a 1M token context, rivaling closed frontier models.
Phonon 2: A 164MB Speech Recognition Model That Runs on Any CPU
Phonon 2 is a 164MB CPU-only speech-to-text model built on Nvidia Parakeet. Here's how to install it and how it performs in real tests.
Running Kimi K3.1 Pro Locally: What the Hardware Actually Takes
Kimi K3.1 Pro is a 2.8 trillion parameter open-weight model. Here's what running it locally actually demands in GPUs, RAM, and money.
Why Do AI Coding Agents Default to Supabase?
Supabase hit 13M users and a million new databases a week. Here's why AI coding agents default to its Postgres backend, straight from the CEO.
Surya OCR 2.5: Local OCR Tested Across Languages and Documents
Surya OCR 2.5 runs locally and reads layout, tables, and text in many languages. Here's how it performs on real documents, warts and all.
The 3D-to-AI-Video Pipeline: How to Keep AI Characters Consistent
How creators turn 3D models from Trippo, Hunyuan 3D, and Meshi into consistent AI video characters across camera angles and scenes.
What Is Recursive Self-Improvement in AI, and When Could It Arrive?
Recursive self-improvement means AI systems helping build better AI. Here's what it actually involves, and why some predict it by 2027.