xixixao

> And we’re introducing a new monthly API credit for our Claude Max and Team subscribers, designed to support our users in building new agents and applications that run on the Claude Platform.

OpenAI really should as this too, even to Plus. I’m already paying more for ChatGPT than I use, give me some free API tokens to play with (there is a free tier for data sharing, but only older text generating models)

It launches on mobile safari but doesn’t seem playable, landscape on mobile safari sucks.

"Topic" is usually covered by branch name. Commit message goes with a set of code changes, it feels more logical to me for the message to describe the actual code as it was written (as it might have changed from the idea phase).

I cannot wait to be past this “here’s a matrix with 40 model options” phase of AI. No “normal” users can tell which choice is optimal for which task.

Example I have worked: Personal delivery app, that tracks packages from various senders using incoming emails.

I am using the single prompt approach with GPT5.4, which is free, but it’s not reliable. Using Jev I’d decompose the prompt into a bunch of smaller questions, then I’d combine the answers in software. I’m super excited to try Jev out.

Tailwind is free. The company’s paid offerings are clearly not useful enough in the world of AI. That’s the crux.

This is such a poor comment. It starts talking about the business model, but it’s just a “Tailwind shouldn’t exist at all” argument. Clearly it’s a useful tool if it’s used by so many people and companies.

You’d have to say which NATO. Czechia is in NATO and was in Warsaw pact.

If you said: Americans usually incorrectly think of Western Europe as those countries not partially or fully under control of the Soviet Union during the Cold War, then I’d agree with you.

Article says Western Europe, but Norway is in Northern Europe.

“First rocket to launch from Europe outside Russia” would have been perfectly correct.

Dumb single sample example: I asked Fable 5.1 to change from hard to soft deletion in an office map backend, and it used soft deletion for data which is synced from another system, but left hard deletion on for the mapping data itself (who sits where). For me it’s a pretty severe lack of judgement (like a red flag if I asked this in an interview).

Very cool!

Note that you can run Convex on top of your own Postgres, and we do this for our internal apps, with very nice performance (plenty for our internal use cases).

In this day and age, where material stuff is so cheap, isn’t 20K for a tiny shed crazy? Clearly it is because it involves so much work, and work is so expensive, but I can’t help but think there should be a technical solution to this. Or buildings are just not automatable? I’m amazed.

People communicate with regards to the audience they expect.

This is why Rust (it’s a systems programming language) and LSP (the language server protocol invented by VS Code) are not explained in the article.

I am hoping I don’t have to define the words I used, but if in doubt, Google or ChatGPT are your friends.

You can do some of this with 1Password as well btw. Looks nice!

Just a little personal tool: Shipment tracking I call Lighthouse:

- All our shipments in one UI (instead of searching trough our mail boxes or going to several merchant apps/sites)

- LLM processes update emails, but everything can be manually adjusted (or created from scratch)

- We have a bunch of destinations we order to (work, home, different pick-up spots), this lets me see where I have to pick up and with which pick-up code

- Real-time sync in case we update something, the other person sees it immediately

- PWA, with animations, feels as good as native on mobile

- $0 running cost (I only paid for AI sub when vibing this)

Desktop: https://imgur.com/a/HD9mCIr Mobile: https://imgur.com/a/EAuJiqH

2 angles I think DB designers don’t often think about:

1. Durability extends to the client. Replicated db might ack a write to client, but what if that ack gets lost on the way back over network? If client talks to the DB over simple HTTP, the write might first look like a failure. Can the client retry?

2. Human perception times are biological and don’t change much. But everything in the tech stack has gotten so so much faster since the 80s. Throughput matters, sure, but latency (relatively speaking), is much less of a constraint now than it was.

jFrog is horrendous, so can you also tackle Python please?

I built myself a package tracking web app. Only cost is LLM sub (Cursor at like $20/m). OpenAI API is free (sharing data). Rest is tailwind+shadcn+Convex - Convex’s free tier is plenty, and it gives me a db and hosting as well now.

I felt the same, but I realized, that if you vibe code more, the changes make sense. Simple example:

Should the AI sidebar be on the left, or on the right? At some point they swapped them automatically, which was jarring (maybe a bug). But now I realize that if I'm not the one primarily writing code and navigating it, then I prefer agents in the "primary" position on the left (esp. if I have the browser on the left half of the screen, the agents are in the middle).

What annoys me the most about Cursor is the random stuff that breaks (due to its nature of VS Code fork).

The tab experience is still unparalleled. The cost might be worse than Codex/Claude sub, but they are all much, much, much cheaper than API pricing, so depends on your POV.

Fixing such issues requires software and site reliability engineering, of which coding is just a part.

The first page of the score card mentions that this model is not capable to replace engineers.

There’s an official Lego boardgame built on this concept.

I would love simpler (harder) instructions! It's too easy tbh brick by brick as it is today. 1964 looks lovely. I also have a gripe with the complexity of modern bricks (besides "basic bricks" sets). It's getting harder to build something else than what the model is.

Can you change the current working directory? If not, it's not a shell script.

1. From the docs: "In the the project it is production ready because it is already used in this context because the shell code generated is tested and confirmed that works, the language is evolving with the tooling set."

Hmm...

2. Support Fish too. Having one language that can generate zsh (macOS default), Fish (power users default), and bash would be really nice!

Looks very tasteful! Good job!

> The government pays Raytheon for missiles, the money cascades down the economy through factories, aluminium smelters, mines, transport companies, all staffed by AIs buying and selling from each other.

This seems too simplistic of a description of how money would work in such a world. Money is just a way to distribute your power to influence people. You never pay for machines or software. Think about buying anything, say a pen. You do not really pay for the metal in the pen. You pay the cost associated with extracting and processing the metal by humans along the production chain. If there were no humans along the chain, the cost could go down to zero.

So far, there are no “AIs” being paid.

The "focus" on planets doesn't work quite correctly. I love that you included true size, but it would be great if the focus worked, and one could zoom between the planets (until the planet shows up).

I also think Saturn's rings don't wobble that fast.

You could sample the informality variable for this font, it might work out.

If Apple could give away a macbook neo to students, locked to the one individual student somehow, for free! they would still make money on it in the long run through the subsequent purchases over the person’s lifetime.

How do you ensure you or your contributors didn’t forget to run the tests?

You’d need at least some hash of sources + test results, and check that it matches that (in CI).

And you’d still deal with environment differences.