danielrm26

Great point. Alternatively, you could have addressed the arguments.

A great point. Yeah, it's not all an articulation issue.

Nobody is saying you shouldn't have a good understanding of the bridge that was built.

The argument is that you need to understand why it failed, in the lifecycle between what we intended to build vs. what we built.

There's a massive difference between a bad design and bad materials, both of which could have caused it to fall.

You can get a bad design idea from the code/bridge as well, but it's pretty glaring when the intent said, "we believe balsa wood is the best bridge material", or "we decided to save 49% of our costs by getting our nuts and bolts from the Lego shop."

Please link the RFC that differentiates the two. And thank you for your service.

Meanwhile thousands of people are using things like prompts and skills and Cowork to do actual work.

If you think this is theoretical at this point it's because you're not using it to do real stuff.

Agreed that there's some measure of chaotic/creative work that won't fall into this type of category.

But much or most regular enterprise work is very much able to be done by having and regularly updating an SOP and then executing the task according to that SOP.

We suck at it. AI will be far better at it. And we'll sit above it and decide how to tweak the SOP based on taste/preference/expertise, whatever.

But the day-to-day work of handling insurance claims, doing procurement, doing analysis, creating reports, processing inputs according to some standard and producing some output according to another standard...that will largely be done by AI.

This is what makes the new /workflows feature coming to Claude Code so exciting (and frightening) to businesses. Along with Skills and Cowork and such, plus their analogs from other providers, Workflows are literally the making of opaque, alchemy-like work that Chris and Raj and Sarah do...into transparent, optimizable algorithms.

It's super hard to automate this stuff because it's super hard to articulate it. That's kind of the meta-super-power in all of this: the fact that AI is making the opaque and complex into transparent and inspectable.

Been waiting 20 years to hear that.

Yes, I could tell. : )

Definitely. We have to find ways to replicate this.

One thing I've noticed is that I've actually learned a lot more code about things I didn't understand before. Just because I built guardrails to make sure that they are built exactly the perfect way that I like them to be built. And then I've watched my AI build it that way dozens of times now. Start to finish. So now I've just seen all the steps so many times that now I understand a lot more than I did before.

This sort of thing is definitely possible, but we have to do it on purpose.

That's why the whole thing has to start with you identifying what you consider core to yourself.

> There is no "separation of moving things on the job vs. moving things at the gym" when it comes to creative craft...

- Coming up with names for cities in a role-playing game you're making - Summarizing an idea that you're writing about - Doing research for an article - Brainstorming character names - Creating an aesthetic for a new website for a customer - Etc, etc.

I could go on for days with these examples. And so could any AI.

Pre-2022 ALL these were done 100% by a human.

Now they're not. Now creative people are using AI to help them massively with tons of these. So, yes, the separation needs to happen there as well.

For example, maybe you say, I'll never use AI to help me name characters. Or to come up with plot lines. Or whatever.

That's a Gym vs. Job distinction.