正在加载视频...

视频加载失败

Vibe coding is harder than engineering You're the: - PM - Designer - Engineer - QA tester Most want it to seem easy, but vibe coding requires an insane attention to detail and curiosity to execute. At the end, you MIGHT have something that works... but it's worth it!

15,786 次观看 • 1 年前 •via X (Twitter)

10 条评论

matt palmer 的头像
matt palmer1 年前

You can find the full video here:

Stefan Ionescu 的头像
Stefan Ionescu1 年前

Attention to detail is key in this game. Vibe coding's a whole different beast from engineering. It's like jazz - you gotta feel it, not just build it.

Jungkeun Hong 的头像
Jungkeun Hong1 年前

@mattppal, such an interesting take on the complexity of vibe coding!

Ben Kaufman 的头像
Ben Kaufman1 年前

I think that’s why I love it so much. I studied CS & business and love coding. I became a PM because it was the best thing that kinda checked both boxes but am always frustrated I can’t spend more time just building stuff. Vibe coding checks everything.

Eve 的头像
Eve1 年前

idk about that lol we can argue about whether the ceiling is higher, but the floor is WAAAAY lower

Michael 的头像
Michael1 年前

True, it requires me to sum it up, break it down, revert to working versions, understand the details of what work and what doesnt because as I mentioned, Replit is like an eager intern. So I need to be very detail oriented. Not to mention different app types require different way

viralarchitect 的头像
viralarchitect1 年前

All of that is part of engineering. I've applied a lot of principals of Site Reliability Engineering when developing with Replit. I love that I get to practice all of the skills in such a tight feedback loop because I am in charge of all of it.

Paco Muro 的头像
Paco Muro1 年前

It's become kind of a mix like a hobbie and the most stressful task i do during my day. Refuse to join vibe-things, you'll never scape.

Girish Kotte 的头像
Girish Kotte1 年前

💯Agree with you

احمد الفهيدي 的头像
احمد الفهيدي1 年前

The annoying thing is that you've finished all the features, and you want to tweak something small but it changes the whole structure

相关视频

BREAKING: GPT-5.5 "Spud" is out and it is a BEAST We've been testing it Every 📧 for the last 3 weeks on everything from coding, to writing, to knowledge work. Here's our day 0 vibe check: - It's a step change in coding AND it's easy to talk to. It's fast and friendly and quickly became my daily driver. But it's also a coding powerhouse—a really rare combination. - It scored 62/100 on our Senior Engineer benchmark. Opus 4.7 scored only a 33/100. (But GPT-5.5 performed best when using an Opus 4.7 plan). Naveen Naidu used over 900 million tokens during testing—and it let him ship production features for Monologue at both high speed and quality. - It has serious conceptual clarity. It can hold a complex plan in its head over hours of work, without getting distracted by existing code. This makes it the first model that we've tested that can perform well on complex refactors requiring deleting and reimagining an substantial existing codebase. - It's a very good writer. This is the first OpenAI model in about a year that got our writers Every 📧 to switch away from Claude. 5.5 has Katie Parrott's seal of approval—not an easy task. Its writing feels more organic and it's better at mimicking a writing style without going overboard. - It's great for agentic knowledge-work. This is the first OpenAI model that manages to be both a stellar senior engineer AND that can be used for everything from spreadsheets to research. It's crazy fast, and it's amazing inside of the Codex desktop app, and got much of our team to switch away from Claude Code and Cowork during the testing period. However, it's not a perfect model. - 5.5 still loses to Opus 4.7 on plan quality. It's plans are extremely readable but Opus has better attention to detail and sharper insight. - 5.5 still loses to Opus 4.7 by a bit on front-end and full-stack product work. Kieran Klaassen found that it wasn't quite as good when full-stack thinking and design are involved. And it's not great writing Ruby. - 5.5 is a great vibe coder but if you're vibe coding without a plan it's worse than Opus. Mike Taylor found that Opus is better at reading in between the lines on underspecified vibe-coding tasks. Overall GPT-5.5 is a massive achievement from OpenAI and it deserves a serious look as your daily driver. Read our full vibe check on Every 📧 here:

Dan Shipper 📧

130,382 次观看 • 2 个月前