kodisha

Fun fact: I spent Sunday afternoon working on this, was sick the week before so I didn't get to spend any claude tokens, so I wanted to go wild and turn Opus/Sonnet to high/xhigh and just prompted it over ~5-6 hours relentlessly.

Once everything was built and deployed it spent ~4% of my $100 claude weekly limit. Actually insane.

What story are they telling them self to justify this?

I just want to leave this comment for future, a and note how news of this magnitude ended up with 2-3 submissions with 15 votes in total.

How come?

Why is this commend downvoted? What is false here?

Yup true, replying to increase visibility in case Zed team is looking at this post. Love the editor otherwise.

Oh no....

I went deep into this rabbit hole and did a lot of reading on how this org is pushing it's agenda in EU.

I hate this Hollywood idiots with burning passion.

LLM driven coding can yield awesome results, but you will be typing a lot and, as article states, requires already well structured codebase.

I recently started with fresh project, and until I got to the desired structure I only used AI to ask questions or suggestions. I organized and written most of the code.

Once it started to get into the shape that felt semi-permanent to me, I started a lot of queries like:

```

- Look at existing service X at folder services/x

- see how I deploy the service using k8s/services/x

- see how the docker file for service X looks like at services/x/Dockerfile

- now, I started service Y that does [this and that]

- create all that is needed for service Y to be skaffolded and deployed, follow the same pattern as service X

```

And it would go, read existing stuff for X, then generate all of the deployment/monitoring/readme/docker/k8s/helm/skaffold for Y

With zero to none mistakes. Both claude and gemini are more than capable to do such task. I had both of them generate 10-15 files with no errors, with code being able to be deployed right after (of course service will just answer and not do much more than that)

Then, I will take over again for a bit, do some business logic specific to Y, then again leverage AI to fill in missing bits, review, suggest stuff etc.

It might look slow, but it actually cuts most boring and most error prone steps when developing medium to large k8s backed project.

> Waiting for downdetector.com to respond...

Very start, 1:34