[caspg]

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).

[MrMcCall]

The problem is that you must understand that 95% in order to complete the last 5%.

[negoutputeng]

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.

[MrMcCall]

Sometimes it's not even inexperienced coders -- it's our own dang selves ;-)

[SketchySeaBeast]

Well, in my mind, the SketchySeaBeast of last week is inexperienced compared to the SketchySeaBeast of this one.

[ericskiff]

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.

[ericskiff]

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.

[trash_cat]

>> 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?

[ipaddr]

I asked Claude AI to make me an app and it refused and called it dangerous. I asked what kind of apps they could build and they suggested social media or health. So I asked it to make one but it refused too dangerous. I asked it to make anything.. anything app and it refused. I told it it sucked and it said it didn't. Then I deleted my account.

I can't think of a worse llm than Claude.

[7thpower]

There have been rumors of the system prompt changing for some services if the user had strikes on their account from earlier conversations. I wonder if you were impacted by this because what you described has not been my experience nor have I seen it discussed previously.

[ipaddr]

I signed up two weeks ago after a hackernews story. I wanted to see quality vs OpenAI. Completely new users first prompt.

[fragmede]

Tbh this sounds like a skill issue.

[ipaddr]

I'm having great success with OpenAI, local llms. I've created semi popular open source project that uses complex prompts to create specialized crms from just a few words.

If ClaudeAI can't create something from my prompts or their own suggestions that's on Claude. Maybe it was my new account on that day at that time. There was a 10 response limit too which made it unworth it to even bother with.

First account I ever actually deleted instead of just never going back. It was that bad.

[fragmede]

Oh I didn't realize ChatGPT was working for you while Claude was not. It's just interesting because my experience is that claude is better at coding than ChatGPT-4o.