prasoonds

I've used LLMs enough that I have a good sense of their _edges_ of intelligence. I had assumed that reasoning models should easily be able to answer this correctly.

And indeed, Sonnet and Opus 4.5 (medium reasoning) say the following:

Sonnet: Drive - you need to bring your car to the car wash to get it washed!

Opus: You'll need to drive — you have to bring the car to the car wash to get it washed!

Gemini 3 Pro (medium): You should drive.

--

But OpenAI 5.2 reasoning, even at high, told me to walk. My first instinct was, I had underspecified the location of the car. The model seems to assume the car is already at the car wash from the wording. GPT 5.x series models behave a bit more on the spectrum so you need to tell them the specifics. So I asked:

"I want to wash my car. My car is currently at home. The car wash is 50 meters away. Should I walk or drive?"

GPT 5.2 Reasoning (medium):

"Drive—your goal is to get the car to the car wash, and it’s only 50 meters, so a slow, careful drive is simplest.

One small optimization: if you’re worried about starting the car for such a short trip or you want to avoid idling in a line, you can walk over first to check if there’s a queue / if it’s open, then come back and drive the car over when it’s your turn."

Which seems to turn out as I expected.

Hey, I’m on mobile right now and can’t remember this off the top of my head. Will check and update in a few hours.

Hey, no. We are not dealing with raw card numbers. It’s just a layer on top of the existing stripe SDK that makes using stripe easier. PCI compliance does not kick in here.

haha yes, it’s definitely a bit of a silly name. The idea is you the user does not have to deal with the webhooks!

That’s a fair point. But of course, this library also helps with other matters - wallets, credits and a code as config based system which can be quite useful too.

And also, if you record all the webhooks events (and a backfill), that basically gives you your whole Stripe data available locally - I’ve actually put it to good use in diagnosing payment failure issues before.

Well it’s a silly name, yes. _You_ don’t have to deal with webhooks - it happens in the background and is taken care of by the library!

Great question. Basically, you would change your billing.config.ts and update the price.

Then, you run the `sync` command - it matches prices by a composite key: `productId:amount:currency:interval`. Since the amount has changed, it won't find a match for the old price. So, it will create a new price in Stripe and update the Price ID. Your new customers automatically get the new price in the Pricing Table component.

Your old subscriptions stay on the old price - which is still active in Stripe. We haven't added support for migrating these customers to the new price yet but it's in the roadmap!

I would like to add that we've tried making the porcelain / user API for the library to best fit today's commonly uses SaaS pricing models so most actions usually do what you would expect (like this price update) but, it's hard to strike a balance between customizability and the _just works_ factor.

Yes, this is one of the bigger use-cases for this library. Lots of folks want custom analytics on their Stripe data and this provides a nice way to do just that.

Let me know how you find it! Happy to implement any fixes and PRs welcome!

Status page results in Vercel's standard 404 page.

Check Down Detector here:

<https://downdetector.com/status/clerk-inc/>

Hi HN, library creator here.

I've linked a demo app linked in the post to try this out:

<https://snw-test.vercel.app>

It uses Clerk for auth and Clerk seems to be having problems:

<https://downdetector.com/status/clerk-inc/>

So if you're having any issues loading the app, you may have to wait a bit!

Hey Felix, yes you can.

This library is simply a wrapper around Stripe with easier implementation and some additional primitives (credits / wallets / real-time usage).

So, just as in Stripe, where you would make a new custom plan for, say, an enterprise use, simiarly here, you'd do the same.

Though, I will admit your `billing.config.ts` file will get pretty crowded...

I will think on it and try to come up with a more user-friendly UX for this use case.

Hey Tony,

yes, the library is ~mostly a wrapper around Stripe with a convenience layer of a simple API that works on the your local DB. So, you will always be able to call Stripe as per usual.

The idea here was to fill the gaps left by the official Stripe implementation:

- direct access to your Stripe data in your own DB - this lets you get around Stripe API rate limits and do custom aggregations (user dashboards? I love what Cursor has done on their usage dashboard for eg)

- easy support for multiple credit types, topups and auto-topups

- usage billing that's much simpler to use (meters, usage products and prices are not exposed to the users)

Other than these basic primitives, everything else is just Stripe under the hood. You can and SHOULD use Stripe SDK for any write operations, for eg.

> This feels like something many teams eventually build internally ...

Exactly right - we've talked to so many teams who has mostly vibe-coded something fragile that mostly works for them and the pattern is common enough that we thought this separate library would be widely useful.

Are you seriously asking why Airport infrastructure should support English or is it rhetorical?

If you are not a backwater that doesn't get any travelers, you should cater to tourists who, as a rule, do not speak your language. Even those tourists who do speak a few phrases will absolutely be unable to understand something as complex as a the train spilling up into two before going to the Airport.

> Why should anywhere cater to my failure to learn their language and systems? It’s nice if they do but I don’t expect it.

I certainly don't see this attitude from Germans in Spain.

This is really cool! I suck at organizing my filesystem and I've lost track of how many times I had to find _that ONE_ PDF which I KNOW I have but cannot find! This would have solved that many times over.

However, at least for my use-case, this is a very infrequent problem. So, a monthly subscription and the security risk wouldn't be worth it. Though I'm certain there are people who work with files all day and for them, this might be god-send!

Right? This one is also very clear ChatGPTese

> That’s not a marginal improvement; it’s a different way of building classifiers.

They've replaced an em-dash with a semi-colon.

Somewhat tangential but I’m curious how people are dealing with these new LLM addons (mcp, extensions for vscode, now CC plugins) at big orgs.

I’ve been using it for personal projects but surely large companies have _some_ way they’re trying to prevent security issues? For instance, I remember one company I worked at blocked us from installing VSCode extensions.

Offering a perspective from Berlin - a decent-to-good senior engineer goes for $120k-$130k so I'm guessing for Warsaw, you could get someone similar for $90k-100k

Really illuminating. Reading the comments, I can't help but think how bad most of us are at predicting the future. While the OP's world might still be somewhat far away, it doesn't seem nearly as far-fetched now as it would have seemed in 2013.

I disagree.

Sonnet 3.6 (the 2022-10-22 release of Sonnet 3.5) is head and shoulders above GPT-4 and anyone who has been using both regularly can attest to this fact.

Reasoning models do reason quite well but you need the right problems to ask them. Don't throw open-ended problems at them. They perform well on problems with one (or many) correct solution(s). Code is a great example - o1 has fixed tricky code bugs for me where Sonnet and other GPT-4 class models have failed.

LLMs are leaky abstractions still - as the user, you need to know when and how to use them. This, I think, will get fixed in the 1-2 years. For now, there's no substitute for hands on time using these weird tools. But the effort is well worth it.

This is really cool! Any chance of adding support for the Arc browser? Right now, Chrome allows for some websites (WhatsApp, Spotify, YouTube Music) to be made into "apps" already via PWAs. Arc - which is based on chromium, for some mysterious reason, chooses to not support PWAs so this would be extremely useful for Arc!

I've heard Rust is especially hard for LLMs, what with the need to thinking deeply about variable ownership and lifetimes. I wonder if it will work better if you try o1-mini (as long as you're still providing the right context!)

And I would've thought that AI would be good at creating new routes (wrap this function in a POST route) - certainly I've done this with Python and TS and it's been fine. Maybe it's a Rust specific issue? Likewise, SQL migrations I would've expected to also just work, especially if your schema change is small! Interesting that it doesn't!

Which tool do you use? Cursor or something else?

Also to add some more context:

- I've found LLM codegen working very well with standard React + TS code

- It sucks when using less knows languages or less popular frameworks (I tried reverse engineering github copilot lua code from the neovim extension in one instance and it really didn't work well)

I'd be curious to hear people's experience here.

Hi, we're working with an large typescript codebase and I develop fully fledged features with Cursor which involve non-trivial UI wiring up work. Decent amount of state management using React too.

It's definitely not boilerplate level code - but it also also stops well short of architecture level work. Here's a recent prompt of me trying to implement line-by-line diff generation: https://pastebin.com/WRJpNwqc

When I need to do architectural/design work, I do it in multiple passes, not generating any code, just lots detailed text with tons of feedback/back-and-forth with the model.

I'm on the pro plan but it's not enough for my needs - I run through the quota in 10-15 days. Then, I revert to using Sonnet 3.5 via API key.

This is cool! I'm a regular user of Cursor (I barely write any code now - just prompt and tab tab tab).

The thing that's really keeping me in Cursor (vs decamping for Zed) is NOT the Cmd K or the sidebar chat. It's actual Cursor's Tab autocomplete model. I've tried many other tab completion models and Cursor Tab blows them out of the water. Supermaven's new release is promising, however.

For the use-case you're solving for (issues with code-privacy), I think something like https://codeium.com/ does already allow for on-prem deployments with enterprise support. I'm trying to think of who would be served well by a fork of VSCode vs Continue.dev or something like a codeium VPS deployment.

Here’s an audio version if anyone prefers listening instead

https://drive.google.com/file/d/1DLtJAShDN54ooPWpBspHPV98rh2...