Over at Hacker News, Claude Code’s Boris Cherney chimes in:

Boris from the Claude Code team here.

Some of the engineers working on the app worked on Electron back in the day, so preferred building non-natively. It’s also a nice way to share code so we’re guaranteed that features across web and desktop have the same look and feel. Finally, Claude is great at it.

That said, engineering is all about tradeoffs and this may change in the future!

There we go: developer familiarity and simpler maintainability across multiple platforms is worth the “tradeoffs”. We have incredible coding agents that are great at transpilation, but there remain costs that outweigh the costs of shipping a non-native app.

Source: Why is Claude an Electron App?

While Drew’s question is around native versus electron apps, I think in it lies a deeper question: If LLMs make the task of coding easier, why don’t developers companies take the time for performance and taste?

I think in it lies a reality that’s often easy to say, but truly hard to grok. There are people who care about the details. There are people who care about the overall impact.

However, companies by definition cannot care for the details beyond a line - as it’s financially unsound. The incremental polish will not be gainful and any time spent on it has an opportunity cost.

Unfortunately, for all the motivation of developers and product owners who care, polish doesn’t get rewarded in promotions for example. This is why polish is always P2 or lower. =(

That said, personally I think LLMs will allow both personal software as well as indie software, where we can reward the people who care about the details.