Whatever it produces still needs to be carefully reviewed and guided. Context switching as a human programmer is very hard so you need to focus on the same specific task, which is harder to not switch to social media or IRL while waiting for it. And you're going to be on the same branch for the same ticket, git doesn't let you do multiple at once (at least I'm not set up to). Not sure where the productivity scaling would come from outside of rapid experimentation on bad ideas until you find the right one, and of course rapid autocomplete, faster debugging, much fancy global find/replace type stuff.

I use it quite aggressively and I'd probably only estimate 1.5x on average.

Not world changing because we all mostly work on boring stuff and have endless backlogs.

I'm starting to lean into just the API tests, playwright tests and keeping the schema solid. I don't have to give a crap about what's in between all that. It's not that simple or extreme but I have a gut feeling we'll just have to get a SLA like mentality and then let it do it's thing to meet these.

Code is not the bottleneck.

> Code is not the bottleneck.

Understanding the problem to solve is.

Yup. Code is liability. Understanding it is the corresponding asset. Generating more code that is less well understood is akin to increasing leverage.

Or: buying a super car might make your commute feel faster. But if everyone did it, we'd have a lot more congestion and a lot more pollution.

Maybe this discrepancy is down to something like Claude code reducing the amount of brain power exhorted. If you have to do 80% less thinking to accomplish a task but the task takes just as long, you may (even rightfully) feel five times more productive even though output didn't change.

And is this a good thing since you can (in theory) multitask and work longer hours, or bad because you're acquiring cognitive debt (see "Your Brain on ChatGPT")?

Exerted, fyi.

Perhaps the hype is not intended for developer consumption, even though often worded as if it were, but instead meant for investors (such as VC's).

Despite living in an age of supposedly transformative brainstorming and creative technologies, we’re also paradoxically inhabiting a time with less creativity and vision than ever. :)

Whaddaya mean, don't you like the 100th live action remake of an old animated movie?

I imagine most CEOs are hyped about serving the same shit sandwich for less money, rather than serving up a tastier sandwich.

Or, as another commenter said, it's for investors, not developers, and certainly not the scum users.

I think it will. The Claude subscription only launched in May. A software company with a large code base, legacy code, paying customers,SOC, GDPR etc is a large boat to turn. I still think we are only months away from realizing the pace you describe