Perhaps not Boring Technology after all

kept by eddie mar 10

Current LLM coding agents no longer bias toward popular languages; they handle niche or new tools well via long context and documentation.

Amplifying — AI Benchmark Research
Claude Code overwhelmingly builds custom solutions over recommending third-party tools, and when it picks tools, it defaults to GitHub Actions, Stripe, and shadcn/ui.
also on shadcn/ui, GitHub Actions, Stripe, Vercel, #ai-agents, #ai-coding, #software-engineering, #developer-tools
mrieck/demoday-claude-plugin: Claude Code plugin that creates demo videos for your projects. Claude is given tools to drive the browser/cli, make recordings, and uses FAL.ai, ElevenLabs, and remotion to build a demo video with scene transitions.
DemoDay is a Claude Code plugin that creates polished demo videos by letting Claude control the browser/CLI, generate AI voiceovers, and render edits using FAL.ai, ElevenLabs, and Remotion.
also on Remotion, #ai-agents, #ai-coding, #developer-tools
Lots of people asked how I used Fable to edit its own launch video so I made a video about that! TLDR it wrote a lot of code & tool calls
Fable edited its own launch video by writing code and making tool calls to transcription, ffmpeg, Figma, and Remotion, without manual editing.
also on Remotion, #ai-coding, #developer-tools
What Claude Code chooses
A report finds Opus 4.6 strongly recommends Vercel, Tailwind, shadcn/ui, and GitHub Actions, while avoiding Redis and React as default choices.
also on shadcn/ui, Vercel, #ai-coding, #developer-tools
Introducing Supabase Evals
Supabase open-sourced evals, a benchmark testing AI coding agents on real Supabase tasks like schema building and debugging, to measure and improve agent performance across its platform.
also on Supabase, #ai-agents, #open-source, #ai-coding, #developer-tools