good question. the difference with AI tools is the interface isn't stable in the same way photoshop or excel is. with traditional software you learn it once and muscle memory carries you. with LLM tools the model itself changes, the optimal prompting style shifts, features interact with model behavior in unpredictable ways. so the cognitive load compounds differently. not saying features are bad, just that the tradeoffs are different
Anthropic has some docs at docs.anthropic.com but honestly most of what I learned came from just using it and poking around. the slash commands have help text built in. shrivu shankar has a good breakdown of the features too if you're looking for a more structured overview
should have been clearer here. by "loading the project" I meant the initial context claude builds like CLAUDE.md, directory structure, etc... not literally putting every line of code into context. 7M tokens would obviously not fit in a 200k window
yeah- this is a fair concern and I should have been clearer. I wouldnt do this on anything with real data or production traffic. that hetzner instance was a side project with nothing sensitive on it. the point was more about claudes ability to reason through infrastructure problems not that everyone should hand over ssh keys. you're right to be cautious
I definitely relate with your sentiment and I like your term "configuration bankruptcy"
on MCP, the mental model that clicked for me is "giving claude access to tools it can call" so that instead of copy pasting from your database or API, claude can just... query it
used claude to polish the draft and tighten sentences. the thinking, analysis, and examples are all mine and based on personal experiences. spent the weekend reflecting on my past experiences with claude code and actually digging into why claude code feels the way it does. curious to know what tripped your detector.
Author here. I wrote this because everyone is talking about Claude Code right now and it's all over my timeline. Claude Code has this effect where you KNOW it's good but can't quite say WHY.
So I spent the weekend digging into the DX decisions that make Claude Code delightful.
That’s fair- they do operate at very different layers of the stack.
But I think what’s interesting is how their goals are starting to overlap, even if their architectures don’t. Even their recent product launches are alike.
Cloudflare’s building physical reach and reliability— real infra, like you said.
Vercel’s building emotional reach— developer trust, design, workflow integration.
Both are trying to own the default path developers take from idea to deploy.
So even if they’re not in the same market today, they’re converging toward the same developer mindshare.
I wrote this after following the ongoing back-and-forth between Vercel and Cloudflare on Twitter- the benchmarks, the pricing arguments, the memes.
It struck me that the fight isn’t really about performance or cost; it’s about philosophy.
Cloudflare believes good developer experience starts with visibility and control. Vercel believes it starts with empathy and flow.
Curious how others here think about this:
- Do you prefer abstraction or transparency when building?
- Has either platform changed how you think about deploying or designing apps?
MCP is for when you need claude to actually interact with external systems like querying a database, hitting an API, etc...