← Back to context

Comment by josephg

2 days ago

I think validation is already much easier using LLMs. Arguably this is one of the best use cases for coding LLMs right now: you can get claude to throw together a working demo of whatever wild idea you have without needing to write any code or write a spec. You don't even need to be a developer.

I don't know about you, but I'd much rather be shown a demo made by our end users (with claude) than get sent a 100 page spec. Especially since most specs - if you build to them - don't solve anyone's real problems.

Demo, don't memo.

7 comments

josephg

Reply
don_esteban  2 days ago

Hm, how much real life experience do you have in delivering production SW systems?

Demo for the main flow is easy. The hard part is thinking through all the corner cases and their interactions, so your system robustly works in real world, interacting with the everyday chaos in a non-brittle fashion.

  • democracy  18 hours ago

    Well he said - anyone can (or will soon) vibe-program their own MS Word - there is no way he is a programmer, sorry. The complexity of these systems is crazy. Unless he meant ah HTML text area with "save" button - then sure, why not.

    • josephg  13 hours ago

      > there is no way he is a programmer, sorry

      Lol I've been programming for 30 years.

      > The complexity of these systems is crazy. Unless he meant ah HTML text area with "save" button - then sure, why not.

      What do you see as the difference between an LLM making an HTML text area and a save button, and an LLM making MS word? It just sounds like a scaling problem to me. We've been scaling computers since long before I was born. My first computer was a 386 with 4mb of ram. You needed a special add-in chip to enable floating point calculations. Now look at what we have.

      As far as I can tell, the only difference between opus 4.6 and some future AI model that could code up MS word is a difference in scale. Are you betting against the entire computing (software and hardware) industry being unable to scale LLMs past their current point? That seems like a really bad bet to me. Especially seeing how far they've come in the last few years. Claude code can already do some quite complex tasks. I got it to write a simple web based email client for me yesterday. It took about an hour in total. It has some bugs, but the email client works.

      We scaled hard drives. We scaled down silicon chips. We scaled digital camera sensors. And display resolutions. And networking bandwidth. We went from the palm pilot to the first iphone to modern phones. Do you really think we'll be unable to scale AI models?

      2 replies →

bavell  1 day ago

Hard disagree, clients/users often don't know what the best/right solution is, simply because they don't know what's possible or they haven't seen any prior art.

I'd much rather have a conversation with them to discuss their current problems and workflow, then offer my ideas and solutions.