Thariq
@trq212
technical staff @anthropicai Made http://tryshortcut.ai at @fundamental, @GoodfireAI, Founder & CEO @OMMultiverse (YC W20), MIT engineer opinions mine
I joined Anthropic last week! It’s obvious to me that we’re bottlenecked not by model capabilities, but by creativity and understanding. I’ll be building demos and prototypes that highlight new capabilities and share what we learn about building using these models at Anthropic.…
This next release of Tidbit is shaping up to be the *single* best way to work alongside Claude Opus. Come see what you can do this Thursday:
hey all. me + @sharifshameem are doing a livestream in 3-days. not a big launch. more like: "hey, here's this ai thing we've been hacking on. what do you think?" we want to: - show you a demo. - share the gritty technical learnings. - tell you how we came up with the idea.…
If I were making a startup today, I would look at what Claude Code power users are doing and then use the Claude Code SDK to turn it into an app that anyone can use without a terminal (docs.anthropic.com/en/docs/claude…) I hope someone steals my video editor idea below...
Use Claude Code as your Video Editor Believe it or not, every video you see below was vibe coded by Claude Code. 🧵 here’s how you can do it too:
Saw @trq212's thread on using Claude Code as a video editor and had to try it myself 💻 Created this @perpflow intro video with Claude Code in ~30 mins. Claude Code: ✅ Set up Remotion from scratch ✅ Coded all animations & physics ✅ Optimized for 2x speed & export
ARC AGI 3 is the first ARC benchmark to require agentic capabilities, because they're games To solve it agents will need to write code, spawn sub agents, and maintain memory I have a feeling the Claude Code SDK is going to be the best way to beat it, stay tuned 👀
Today, we're announcing a preview of ARC-AGI-3, the Interactive Reasoning Benchmark with the widest gap between easy for humans and hard for AI We’re releasing: * 3 games (environments) * $10K agent contest * AI agents API Starting scores - Frontier AI: 0%, Humans: 100%