Orchun Kolcu

@PragmaticAndy When you brought up how backwards it is for colleges to look for high math scores when the main skill needed is communication... I recalled a conversation I had with my manager back when I was involved in hiring. We weren't having a lot of success, so trying to figure out better ways to identify high value candidates, I suggested instead of trying to come up with convoluted questions and coding tests, why don't we simply begin with having them write down, in as much detail as they desired, what they could do for the business. And he dismissed it, saying people don't like to write and we'd just lose more people in the pipeline. He didn't think of not being able to or willing to express yourself as a red flag for a developer...

@siderea On Android Bitdefender anti virus free is the least scammy. Can't speak to its efficacy.

@thirstybear I have a feeling nobody would have implemented worktrees if they thought the use case would be "handing off to an agent".

RE: @jbrains@mastodon.social

I actually did this with JB for about a year when I felt stuck with "intermediate blues" and it was great. I actually think it's suitable for all levels. There are a lot of unique things about it:

- He doesn't tell you "make sure your functions are no bigger than 5 lines". He goes into the heart of the matter keeping a perspective of what actually makes a difference.
- He is a very good communicator.
- You get to interact with others drawn to this kind of training
- You get very good access to him
- It's great value.

@RobMyers@mastodon.social What I want to start with is coding (vs gherkin) the acceptance tests myself (which would be subcatenous) so retain a modicum of control over the code design. And of course with very incremental spec/deliverables. But my curiosity is really about whether mutability testing would practically work for forcing the LLM to generate exhaustive unit tests, and whether it (and I) can deal with managing the over specification of tests it would undoubtedly create.... After all, if I don't review the tests, all I'm gaining is regression control, not correctness. To switch the topic a bit... I'm no conspiracy theorist but I think there is a very very real danger of becoming LLM dependent here. Right now all the fervor towards LLM use assumes inference costs stay cheap. What happens when people/orgs are hooked and can't do without LLMs but the costs are now real?

@RobMyers@mastodon.social I've given up on TDD with it but there is a workflow I would like to try - it's the second post here: https://hachyderm.io/@orchun/116217583464911995

@RobMyers@mastodon.social Do you think the results would have been any different if you didn't ask for "TDD" but just asked it to write tests and make them pass?

@RobMyers@mastodon.social Congratulations on the book! 🥳 I'm just at the point where it starts churning out code, but.. predictably it goes sideways from the get go. You wouldn't write that coordinates story. If you wrote that test, that's not what you'd call it and you wouldn't write that implementation (with more code than the test demanded) and you definitely wouldn't have just a single test for that story... EDIT: or maybe I'm completely wrong and it is doing a much better job off screen.. let's finish the video 😁