Most of software work is maintaining "legacy" code, that is older systems that have been around for a long time and get a lot of use. I find Claude Code in particular is great at grokking old code bases and making changes to it. I work on one of those old code bases and my productivity increased 10x mostly due to Claude Code's ability to research large code bases, make sense of it, answer questions and making careful surgical changes to it. It also helps with testing and debugging which is huge productivity boost. It's not about its ability to churn out lots of code quickly: it's an extra set of eyes/brain that works much faster that human developer.

Completely agree. In the past 12 months, I've had five or six use cases that I would not have bothered scripting or automating before, but I've cranked out scripts or even small web services in under an hour that get the job done using AI. It has really revolutionized the super small bite-sized issues

Well said. The cost of building a CRUD has dropped 90%.

The open question is why people needed fancy AI tools like Claude to write CRUDs in the first place. These kind of tasks ought to be have been automated a long time ago.

Most code is simple, the fact that large complex systems are layers of simple code on top of itself, like garbage heaps at the dump, makes it complex. Sticking with the garbage analogy, the LLM is like upgrading from one shovel to an crew of 10 people with excavators to look for a lost Bitcoin hard drive.

Your project is still going to fail, but it will fail faster with the 10 excavators.

At the leafs of the branches I'm comfortable to just generate code (e.g. a popup dialog). But I want to have a good grasp of code that is central of the application.

> The cost of writing simple code has dropped 90%.

Need to add, “…and what ‘simple’ means is getting broader by the day.”

While I would love for this to be true for financial and egotistical reasons, I have a growing feeling that this might not be true for long unless progress really starts to stall.

And not everyone wants to use a cloud AI either. Remember that when tons of cash is on the table, things like license agreements become less enforceable and more of a "don't get caught in the cookie jar" thing. All it would take is something similar to what's going on with book authors/publishers - a major AI provider exposed as using other firms' proprietary code without even considering to get a license - to totally blow up the "safety" of cloud based coding agents.

Local models are becoming more and more capable but the tooling still needs to get better for those.

I’ve found they are able to compose well, let it build small components and stitch them together

Yes, well, I think this makes that skill of problem reduction a very valuable skill.

Yes, but for experienced engineers that is still a huge huge change .

Even 12 months ago simplifying tasks alone was insufficient, you still needed a large group engineers to actually write, review and maintain a typical product for solid startup offering. This came with the associated overhead of hiring and running mid sized teams.

A lot of skilled people (y)our age/experience are forced into doing people management roles because there was no other way to deliver a product that scales(in team and complexity not DAU).

A CTO of mid-stage startup had to be good architect, a decent engineering manager, be deeply involved in product and also effectively communicate with internal and external customers.

Now for startups setting up new you can either defer the engineering manager and people complexity lot latter than you did before. You could have a very senior but small team who can be truly 10x level and be more productive without the overhead of communication, alignment and management that comes with large teams.

----

tldr; Skilled engineers can generate outsized returns to orgs that set them up to be successful(far more than before), I can't say if compensation is reflecting this yet, if not it soon will.

> The cost of writing simple code has dropped 90%.

Plus there's a lot of simple code you shouldn't be writing either way, because it's in a library by now.

By their nature, LLMs will do their best with things that could be plagiarized.

I would add "predictable" to that as well.

I fed Claude Pro a REST API spec and told it to spit out a Powershell module and well... So far that 27k lines of code largely checks out (minus the undocumented stuff I knew about).

Getting it to write the pester scripts was a very different matter...

[dead]