korrents

korrents · video

How To Get The Most Out Of Vibe Coding | Startup School

Tom Blomfield · 16m · youtube.com ↗

19 korrents from this recording

Tom Blomfield did not write this page.

Every claim below is a statement made in this recording, quoted word for word and linked to the second it was said, so you can hear it rather than take our word for it. The wording comes from the transcript published alongside the recording; the sentence above each quote is our reading of the claim, not their wording.

  1. 0:16 · watch on youtube.com↗

    I found not only is it remarkably good, but it's also a practice you can get measurably better at if you're open to tinkering and picking up best practices.
  2. 0:37 · watch on youtube.com↗

    The best techniques are the same techniques that a professional software engineer might use.
  3. 4 min later
  4. 4:25 · watch on youtube.com↗

    Many product managers and designers are actually going straight to implementation of a new idea in code rather than designing mock-ups in something like Figma just because it's so quick.
  5. 1 min later
  6. 4:59 · watch on youtube.com↗

    Once you've picked the tool you want to use, the first step is not to dive in and write code. Instead, I would work with the LLM to write a comprehensive plan.
  7. 1 min later
  8. 5:58 · watch on youtube.com↗

    I probably wouldn't expect the models to oneshot entire products yet, especially if they're complicated.
  9. 6:26 · watch on youtube.com↗

    Version control is your friend. Use Git religiously.
  10. 6:51 · watch on youtube.com↗

    I found I had bad results if I'm like prompting the AI multiple times to try to get something working. It tends to accumulate layers and layers and layers of bad code rather than like really understanding the root cause.
  11. 1 min later
  12. 7:28 · watch on youtube.com↗

    Although they often default to writing very low-level like unit tests, I prefer to keep these tests super high level.
  13. 7:52 · watch on youtube.com↗

    LLMs have a bad habit of making unnecessary changes to unrelated logic.
  14. 1 min later
  15. 9:10 · watch on youtube.com↗

    Often this error message is enough for the AI to identify and fix a problem.
  16. 9:22 · watch on youtube.com↗

    pretty soon I actually expect all the major coding tools to be able to ingest these errors without humans having to copy paste.
  17. 1 min later
  18. 10:20 · watch on youtube.com↗

    I often find that um different models succeed where the others fail.
  19. 1 min later
  20. 10:53 · watch on youtube.com↗

    I know founders who've written hundreds of lines of instructions for uh their AI coding agent and it makes them way way way more effective.
  21. 11:17 · watch on youtube.com↗

    some people are suggesting uh using an MCP server to access this documentation, which works for some people. Uh seems like overkill to me.
  22. 1 min later
  23. 11:54 · watch on youtube.com↗

    It's a great way to learn new technologies. It's much better than scrolling Stack Overflow like uh we all used to do.
  24. 1 min later
  25. 12:39 · watch on youtube.com↗

    Remember, small files and modularity are your friend. This is true for human coders as well.
  26. 12:44 · watch on youtube.com↗

    I think we might see a shift towards more modular or service-based architecture where the LLM has clear API boundaries that it can work within while maintaining a consistent external interface rather than these huge uh monor repos with massive interdependencies.
  27. 1 min later
  28. 13:34 · watch on youtube.com↗

    I think this is because Rails is a 20-year-old framework with a ton of wellestablished conventions.
  29. 1 min later
  30. 14:56 · watch on youtube.com↗

    And the AI is so tolerant of minor grammar and punctuation mistakes that it honestly doesn't matter if the transcription's not perfect.