←back to thread

Claude AI built me a React app to compare maps side by side

(github.com)
221 points caspg | 8 comments | 17 Nov 24 13:39 UTC | HN request time: 0.001s | source | bottom
Show context
caspg ◴[17 Nov 24 13:39 UTC] No.42164142[source]▶
I wanted to develop a simple tool to compare maps. I thought about using this opportunity to try out Claude AI for coding a project from scratch. It worked surprisingly well!

At least 95% of the code was generated by AI (I reached the limit so had to add final bits on my own).

replies(2): >>42164624 #>>42164812 #
1. MrMcCall ◴[17 Nov 24 15:22 UTC] No.42164624[source]▶
The problem is that you must understand that 95% in order to complete the last 5%.
replies(4): >>42164697 #>>42164702 #>>42164767 #>>42166353 #
2. negoutputeng ◴[17 Nov 24 15:34 UTC] No.42164697[source]▶
exactly right.

POCs and demos are easy to build by anyone these days. The last 10% is what separates student projects from real products.

any engineer who has spent time in the trenches understands that fixing corner cases in code produced by inexperienced engineers consumes a lot of time.

in fact, poor overall design and lack of diligence tanks entire projects.

replies(1): >>42164739 #
3. ◴[17 Nov 24 15:34 UTC] No.42164702[source]▶
4. MrMcCall ◴[17 Nov 24 15:42 UTC] No.42164739[source]▶
Sometimes it's not even inexperienced coders -- it's our own dang selves ;-)
replies(1): >>42167099 #
5. ericskiff ◴[17 Nov 24 15:46 UTC] No.42164767[source]▶
Interestingly, I’m pretty sure they mean they hit the limit with tokens on Claude.

There’s a daily 2.5 million token limit that you can use up fairly quickly with 100K context

So they may very well have completed the whole program with Claude. It’s just the machine literally stopped and the human had to do the final grunt work.

replies(1): >>42164771 #
6. ericskiff ◴[17 Nov 24 15:47 UTC] No.42164771[source]▶
We’ve been hitting this in our work and in experimentation, and I can confirm that Claude sonnet 3.5 has gotten 100% of the way there, including working through errors and tricky problems as we tested the apps it built.
7. trash_cat ◴[17 Nov 24 19:24 UTC] No.42166353[source]▶
>> The problem is that you must understand that 95% in order to complete the last 5%.

What stops you from using AI to explain the code base?

8. SketchySeaBeast ◴[17 Nov 24 20:49 UTC] No.42167099{3}[source]▶
Well, in my mind, the SketchySeaBeast of last week is inexperienced compared to the SketchySeaBeast of this one.