We started using Claude code at work.
-
We started using Claude code at work. In a reasonable way, I must say: let's give it a spin, see what it can do for us, treat it as a tool in the toolbox, not a developer-displacing silver bullet, etc.
Anyway, I was working on a ticket, took time to install the CLI, and then asked it to generate a test for some new code I wrote (usually I TDD, sometimes I code my way first to a solution, it depends. No silver bullets, just tools in the toolbox).
What happened next made me giggle, because the test was hilariously bad and full of all sorts of antipatterns.
What happened _next_ made me cry. I realized that Anthropic just scraped all the Elixir code it could get its hands on so the style of test its product generates reflects the general "state of the art" in the Elixir community.
Realizing that made me very sad. I guess it's time to write a blog post on proper test approaches in Elixir (too bad I cannot use Claude's code as a showcase as it is work code, it'd be a great exposition piece).
(cont)
-
R relay@relay.mycrowd.ca shared this topic
-
We started using Claude code at work. In a reasonable way, I must say: let's give it a spin, see what it can do for us, treat it as a tool in the toolbox, not a developer-displacing silver bullet, etc.
Anyway, I was working on a ticket, took time to install the CLI, and then asked it to generate a test for some new code I wrote (usually I TDD, sometimes I code my way first to a solution, it depends. No silver bullets, just tools in the toolbox).
What happened next made me giggle, because the test was hilariously bad and full of all sorts of antipatterns.
What happened _next_ made me cry. I realized that Anthropic just scraped all the Elixir code it could get its hands on so the style of test its product generates reflects the general "state of the art" in the Elixir community.
Realizing that made me very sad. I guess it's time to write a blog post on proper test approaches in Elixir (too bad I cannot use Claude's code as a showcase as it is work code, it'd be a great exposition piece).
(cont)
@cdegroot Regression to the mean codified
-
@cdegroot Regression to the mean codified
@krono yup.
To be fair, I think a lot of Elixir teams work on what I call "one-shot webapps". The sort of tests that Claude essentially told me are commonplace are fine for that. But in the context of an ISV or SaaS company... it'll kill your productivity.
