6-7? No, my kid says it about a thousand time a day. Then, for some unknown reason they follow it with 41! WTF! I've shouted 42! many times and have tried to inform the child of the significant cultural and scientific importance of 42. Which, IIRC, factors to 2,3,7.
The step you describe is the main use case I’ve found where vibe coding actually makes sense. Going from there to actually make a good version of the thing then becomes more hands on.
I’ve done a lot of vibe coding and I just can’t understand these takes. Pure vibe coding is not going to get you to a good result, so the alchemist you describe is still very much essential, and as far as I can see will be for a very long time.
Not really. You have to pivot to a systems designer role and articulate in detail what you want to build, but the building of it is now effectively automated. Most programmers are not ready for this shift in mindset. Their perceptions of their own competence (hence value to organization, hence self-worth) are tied to writing the code. Hence why AI-assisted coding seems so unfun.
“It's redundant to say "I think" at any point in an opinion piece.”
“But is there still value in human produced writing? Subjectively, yes. Objectively? I'm not sure. I think there's a lot of personal value in writing though.”
There is value because I felt compelled to engage, but if it turns out you’re a bot then I’ll feel cheated and less likely to read other blog posts.
yea, I'm not saying there's no place for that phrase ever. But overusing it was a bad habit of mine and it ends up being unnecessary filler. My wording there was a bit exaggerated.
how will people sharpen their thinking if they don't write their own words? the value in human writing even with llms remains almost the same. you won't get better stuff without it
It definitely has its amazing moments, but sometimes I get caught in a loop of expecting it to do the thing, it not working, and spinning my wheels a lot instead of just solving it myself. I think I’m still learning how to use the tools effectively, but the random nature of it makes it difficult.
The more I interact with these the less I’m afraid these tools will make life meaningless. (Can’t speak on art generation tools. Those still depress me.) It doesn’t matter what you’re making there are still a lot of hard parts even with the best versions of these tools. I doubt a good software developer can be replaced totally unless these get way better.
The best use cases are for code that’s clearly not an end product. You can just try way more ideas and get a sense of which are likely to pan out. That is tremendously valuable. When I start reading the code they produce, I quickly find many ways I would have written it differently though.
Have you tried claude code? I despise AI to my bones but even I can’t say claude code is not impressive.
If any anthropic reps read this, I think you guys, while probably better than open AI and meta, possibly Google, are delusional and are more likely to destroy the world than create infinite human life.
I have and it is. But I did acknowledge that in the previous post. I just don't think software development tools like Claude Code, while great, and I wouldn't want to back to life without them, are going to recoup all this investment. We need like 10 Claude Codes for different aspects of work and life. Then we're getting somewhere...
reply