mastodontech.de ist einer von vielen unabhängigen Mastodon-Servern, mit dem du dich im Fediverse beteiligen kannst.
Offen für alle (über 16) und bereitgestellt von Markus'Blog

Serverstatistik:

1,5 Tsd.
aktive Profile

#aicoding

5 Beiträge5 Beteiligte0 Beiträge heute

Software innovation might be freezing in place—and AI could be to blame. Theo Browne points out that Copilot and ChatGPT often return React-style code even for Solid or Elixir projects. Why? Because they’ve seen React a million times more. Python 3 took a decade to overtake Python 2. If that transition had to happen today, would our dependence on AI suggestions keep us from making the jump?

linkedin.com/posts/jonippolito

It's also time for me to jump on the bandwagon of AI coding. In the past, I was using Copilot, and it was rather bad experience, but not always.

If you'd have to choose one, what would you choose? Copilot, Cursor, Claude Code, something else?

I'm #nvim user, so using Cursor would require from me to change my editor, and I'm not sure if I'm ready for it.

Is there anything else I could use with nvim on flat subscription except for GH Copilot?

#ai#coding#aicoding

"Finally, the most accessible option is “no-code” products like Replit and Lovable, which live in the web browser and are optimized for non-engineers. You can brainstorm a quick prompt like, “Make me a website to display the new albums I listen to each month,” and within minutes, get a functioning website and URL.

This approach has been dubbed “vibe coding” by Andrej Karpathy, an AI researcher who was on the founding team of OpenAI and led AI at Tesla. AI coding programs “are getting too good. I barely even touch the keyboard,” he wrote on X.

There has been a lot of speculation about how AI coding will help companies to create software in a leaner, faster way—and how it could threaten jobs for junior engineers. In April, Microsoft CEO Satya Nadella said that up to 30% of code at Microsoft was already written by AI. Meta CEO Mark Zuckerberg expects AI to code at the level of a “midlevel engineer” by the end of the year.

But the most important effect of inexpensive AI coding tools may be to bring software development to the masses, no computer science degree or billion-dollar revenue plan required. To borrow an analogy from the author and programmer Robin Sloan, AI might enable more people to program like a “home cook”—having fun making apps for their own household and community—instead of relying on fast-food operations that churn out generic apps at industrial scale."

wsj.com/tech/ai/your-next-favo

#AI#GenerativeAI#VibeCoding