I had a problem with signing up for max with the wrong email, then thinking I didn’t actually do it, so I signed up with the one I wanted.
Saw the double bill and contacted them, I had a full refund in a couple days and a nice personal note thanking me for being a max user.
This was a couple months ago so it’s possible they’ve had a huge influx of requests that made it difficult to respond fast lately but I had a good experience with their customer service.
It still implies possibility of failure, but in the example of the commenter above, that possibility is almost low enough to the point of expectation (but not quite) and "try to" would increase that possibility in the direction of failure. Nuance!
Is it possible to view the prompt history? I’ve had extreme levels of productivity and would love to list out how I’ve been using it generally for an article like this but it would be incredibly impractical to log it on the side.
With Claude Code at least, all of the chats you've had are stored in jsonl files on your computer in ~/.claude - I made a little TUI for exploring these in https://github.com/orta/claude-code-to-adium
Personally, I'm less sold on tracking prompts as being valuable both for production cases (imo if a human should read it, a human should have wrote/fully edited it applies to commits/PRs/docs etc) and for vibe cases where the prompts are more transitory
I really want to record a live commentary of me working with claude. Maybe that's something you could think about.
I feel like the results I get are qualitatively superior to anything I've seen anyone I've worked with produce. The fact that it's a lot faster is just gravy on top.
This is the saddest part of this whole thing for me. You consider the prompts and config to be the real source code, but those are just completely lost into the ether. Even if you saved the prompts you can't reproduce their effects.
Then there's the question of how do other developers contribute to the code. They don't have your prompts, they just have the code.
So, no, prompts are not source code, that's why I ask for people to just show the code they are producing and nobody ever does.
I also make my design documents (roughly the prompts generated by the prompts) into committed markdown documents. So I show the second-tier prompts at least, you could consider those an intermediate language representation if you like.
> Then there's the question of how do other developers contribute to the code. They don't have your prompts, they just have the code.
I usually try to commit the initial prompts and adjustments. I don't commit trivial things like "That's not quite right, try doing X again" or "Just run the entire test suite"
This is a fair point, but the analogies to vehicles don't really work anyway: they're a depreciating asset, houses are not. Even a tiny rundown place can cost millions owing to location.
But all things held equal, if you have a new house that's big and a new house that's small, the smaller one is cheaper. And further, mixed density builds will be cheaper than single detached homes. Beyond that there's nothing caked-in to the walls that makes a house cheaper or expensive. Shitty houses are just unmaintained, dilapidated. Flooding the market with houses will drop prices.
You just described what I do with my ultrawide monitor and laptop screen.
I can be fully immersed in a game or anything and keep Claude in a corner of a tmux window next to a browser on the other monitor and jump in whenever I see it get to the next step or whatever.
It’s a similar idea, but imagine you could fire off a task, and go for a run, or do the dishes. Then be notified when it completes, and have the option to review the changes, or see a summary of tests that are failing, without having to be at your workstation.
You can do this today with OpenAI Codex, which is built into ChatGPT (and distinct from their CLI tool, also called codex). It will allow you to prompt, review, provide feedback, etc via the app. When you're ready, there is a GitHub PR button that links into a filled out pull request. It has notifications and everything.
There are a handful of products that all have a similar proposition (with better agents than OpenAI frankly), but Codex I've found is unique in being available via a consumer app.
I mean, windows users install things they’ve never heard of all the time.
If this was a real thing you needed to do, and it is too much work to get them to install WSL, you could probably just send them the link to install Git and use git bash to run that curl install sh script for dumbpipe.
And if this seemed like a very useful thing, it couldn’t be too hard to package this all up into a little utility that gets windows to do it.
But alas, it remains “easier” to do this with email or a cloud service or a usb stick/sd card.
Europe is the world‘s second largest economy and has the world‘s highest standard of living. I’m far from a fan of regulation but they’re doing a lot of things right by most measures. Irrelevancy is unlikely in their near future.
Saw the double bill and contacted them, I had a full refund in a couple days and a nice personal note thanking me for being a max user.
This was a couple months ago so it’s possible they’ve had a huge influx of requests that made it difficult to respond fast lately but I had a good experience with their customer service.