Destiner

Did they just want to hire some extra skilled engineers?

This. Probably to work on Anthropic's SDKs and tooling.

makes sense, it kinda not super useful once xcode added native AI coding features

There's Alex (https://www.alexcodes.app), YC-backed.

Most likely a CSS rendering issue. I'm seeing proper/normal output on macOS Safari.

Claude is omitted, because Claude is the only agent that still doesn't support the standard filename convention.

The text rendering is impressive, but I don't understand the value — wouldn't it be easier to add any text that you like in Figma?

I bought a life-time plan a few years ago.

Feels like a no-brainer investment.

I don't think an LLM would recommend an edit like that.

Has to be a bug in their rule-based system?

one good technique is to pass the style guide as a json, where you define materials, lightning, perspective, etc

you can even use a vision model to generate the style guide for you

honestly a power move.

it's almost as if they don't care about creating a proper buzz.

I’ve just used BetterAuth for my project [0]

I’ve never implemented auth before, and was always thinking that it will take me days to get it right.

I’ve done the whole thing in maybe 3 hours.

[0] https://dough.ink/

I think you're describing NIMBY, which is more of a US/SF thing (but also is a case in Europe to some extent).

This is great for RAG, but Claude is generally hard to use for many cases due to lack of the built-in structured outputs.

You can try forcing it to output JSON, but that is not 100% reliable.

all this WP drama makes me really grateful about deciding to go with a static site generator.

Astro FTW!

perplexity is a great product, but it's a feature, not the app.

they are in the middle — not really a lab, not really a consumer product.

i expect them to get acquired in the next year or so.

At that point, why not just send me a set of bullet points and the presentation or screenshots?

Because video works better for product demos.

Show, don't tell.

you're not a target customer anymore.

they need $$$ from enterprise, everything else is a distraction.

I love when somebody disrupts a hidden market like that. Fandom had terrible UXs for years, but nobody seemed to care enough to make an alternative. I'd assume most users are not engineers/founders, so the opportunity was hidden for a while.

In hindsight it makes total sense.

as somebody who spent many years writing "regular" css, this is magic

i wonder if we start to see the "css engineer" job posts sooner or later

great initiative, i wish larger companies would join

not a single word about anthropic/claude?

makes you wonder about the level of journalism at wsj et. al.

i feel bad for kagi/ddg

they are still trying to fight the google by building pretty much the same product

while perplexity is obviously in the lead by being ai-first

Related: Keygen is also Fair Source now (https://keygen.sh/blog/keygen-is-now-fair-source/)

how it’s a win if i can’t use apple products?

I use Safari almost exclusively for all desktop browsing, and haven't seen fully broken or even mildly broken websites in years.

I think what helps a lot is that if it's broken in Safari on macOS (not a big deal for the business), it would also be broken in Safari on iOS (which would be a disaster).

We use the excellent sqlx Rust package to handle migrations.

The JSR API server is written in Rust, using the Hyper HTTP server. It communicates with the Postgres database via the sqlx Rust crate.

Looks like most of the backend is written in Rust. Must be a bummer working on a JS runtime, and not being able to test it out at such a scale.

Here's an elevator pitch. Your twitter/facebook/github account gets banned, what do you do? With farcaster/lens/radicle, it's impossible.

I've been using Zed for the last few months, and it's amazing, very fast and clean.

My only worry is that the collaboration features won't be used much, as they require most of the team to use Zed.

In Western countries and other liberal democracies, estimates for the value of a statistical life typically range from US$1 million—US$10 million; for example, the United States FEMA estimated the value of a statistical life at US$7.5 million in 2020

Woah that's tiny.

not really, those tools somewhat overlap, but they have completely different purposes (formatting vs linting)