this post was submitted on 15 Sep 2025
135 points (82.6% liked)

Technology

75162 readers
1580 users here now

This is a most excellent place for technology news and articles.

Our Rules

  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

founded 2 years ago
MODERATORS
L3s@lemmy.world
enu@lemmy.world
technopagan@lemmy.world
L4s@lemmy.world
L3s@hackingne.ws
L4s@hackingne.ws
135
Vibe coding has turned senior devs into ‘AI babysitters,’ but they say it’s worth it | TechCrunch (techcrunch.com)
submitted 22 hours ago by kinther@lemmy.world to c/technology@lemmy.world
70 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] Simulation6@sopuli.xyz 7 points 14 hours ago (3 children)

I have never tried to use AI to develop software, just looked at the output that sometimes shows up in google searches. Noises are starting to come from on-high about an AI 'push', so I may need to show some basic awareness. Any suggestions on how to get started or should I just ask the AI?

[–] thirteene@lemmy.world 6 points 11 hours ago

I've been using copilot. Potential is there but getting a result is more art than science. I've found it helpful to document desired workflows in readmes and ask for unit tests then run unit tests until it works out.

  • use a premium model like sonnet and put it in agent mode
  • Ask it to review the project
  • ask it to review the ticket/requirements
  • ask it to research existing solutions and write a design document that meets the requirements with high certainty
  • Let it write the document and make sure it stays on task
  • review the output and send build errors back, roll forward or undo the code and re-submit
  • identify what works and reduce scope
[–] cevn@lemmy.world 4 points 10 hours ago (1 children)

I will say Claude Code may be at the fore front of AI coding assistants. It runs in your terminal. Try loading it on one of your side projects and see what you can accomplish.

[–] Ghostie21@lemmy.world 1 points 9 hours ago* (last edited 9 hours ago) (1 children)

Is there a difference between claud in the vscode extension and Claude code? I mostly use chat mode but will sometimes try agent and neither really make me happy. Id say if a task could be given to a high school programmer the AI agents can do it about 30÷ of the time.

[–] cevn@lemmy.world 1 points 8 hours ago

I feel like the experience is different and it feels more integrated with the project than simply running a claude model with Cursor which is a vscode fork. Right now I had it working on a long running cli app task in Rust and its been implementing feature after feature consistently.

[–] percent@infosec.pub 2 points 12 hours ago

I'd suggest Cursor. I was somewhat anti-AI-coding until my job encouraged it, and Cursor (using Claude 4 Sonnet) gave me that "ohh, now I get it" moment.

It's still plenty capable of generating bad code, so it can take a bit of practice to get a feel for how to use it productively.