jf22

I like AI tools. I'm bullish on AI tools. I'm productive with AI tools.

But...

At my job the prevailing sentiment is everything should be easy and fast with AI now so why bother doing anything that can't be done with AI.

Talking with customers can't be done with AI so we'll just ask Claude what our customers think.

Collaborating on a new product design together can't be done with AI so we'll just ask Claude to design it.

Strategy is hard so we'll just chat with Claude about what we should do and accept the output.

And so people generate a bland ticket with Claude and I'm asked to implement completely "souless" feature that is generic and boring and not important to anybody.

Oh and it should only take a few days because code is free now.

We ship it, nobody cares about it because the only thing that's put in any effort is an LLM, and move onto the next thing.

Before LLMs features had humans attached to them and working together to get them out the door meant something. Plus, a lot more effort went into to making sure it was the right feature and a good product because all the people involved wanted their name to be associated with success.

With LLMs nobody cares if the LLM was wrong, its the LLM that was wrong not Jacob or Jamie.

It's like we are producing empty shells of technology. The code is there and the feature is there, but nobody cares. Even the customers don't care because we ship a thing nobody wants and we tell people about it with bland generated marketing and announcement documentation.

And yeah. I'm super productive and shipping more and more and more and more features but I feel like I've done is ship skeletons of web apps when before I used to ship living breathing applications.

But we aren't cooking with gas. We are cooking with a more controlled burner than ever that can download a clean code claude skill and be committing better code than you or I could write.

What would normally be considered overengineered gold plating is "free" now.

First, most software is already a hot mess.

Second, LLM code can be less of a hot mess than human written code if you put in the time to train/prompt/verify/review.

Generating perfect well patterned SOLID and unit tested code with no warnings or anti-patterns has never been easier.

What do you mean?

What's a good example of human-led design?

I'm interested to know why you think data structures are important. AI is pretty good at reasoning out data structures problems.

If there isn't a phrase then just say the numbers...

You can tax reach though.

The "overwhelming majority" standard for harm seems odd when you use 15% of smokers getting harmed as an example. 15% is not an overwhelming majority.

We are way past this question now.

I kept a personal license for while because I thought Windsurf kept memories a little better than Claude.

But now since I use Claude at work I switched to keep my home and work stacks similar.

All that cleanup can be done with AI and then you can add guidance to the codebase so that the next LLM will do a better job at conforming.

We are not.

I feel like I'm a stone skipping across the water instead of being submerged deep in coding context.

I'm getting used to it but I don't like it.

I'm also much more tired at the end of the day. My mind feels broken. I don't know if our brains were designed for this.

How are the architecture changes you are proposing improving the end result?

but not being able to control the exact output worries me

Why?

I have a physical goods side hustle already and I'm brainstorming ideas about a trade I can do that will benefit from my programming experience.

I'm thinking HVAC or painting lines in parking lots. HVAC because I can program smart systems and parking lot lines because I can use google maps and algos to propose more efficient parking lot designs to existing business owners.

There is that paradox when if something becomes cheaper there is more demand so we'll see what happens.

Finally, I'm a mediocre dev that can only handle 2-3 agents at a time so I probably won't be good enough.

I don't understand he comment.

AI produces code that people can understand and is easy to maintain if you ask it for that.

I'm an 99% organic person (I suppose I have tooth fillings) and the new models write code better than I do.

I've been using LLMS for 14+ months now and they've exceeded my expectations.

I'm a former EM who would never go back in an AI age.

EMs deal with friction and from my experience more output is more friction.

You have org leaders and businessy people putting their foot on the gas because AI is so productive and then programmers shipping 2-3x more code.

These two forces collide and you're stuck dealing with the friction so 10x the amount of initiatives you did before.

The friction is like sandpaper on sandpaper.

This is a really bad take (and bad faith) because all the failed tech initiatives you mentioned barely had any adoption whereas LLM based AI tools are used by a billion people a week.

I think the question is why didn't you ask the AI and then if you need more information ask the human including what you learned from AI.

Humans, with reliability, will ignore the patterns or best practices in your code and implement the same thing twice in different ways.

In 25 years I've never worked in a codebase where this wasn't true.

Sure but in my experience LLMs behave much more consistently than humans with regards to quality. LLMs don't skip tests because they have to make a deadline for example.

And now we have LLMs that review LLM generated code so it's easy to verify quality standards.

You can tell LLMs to conform to certain quality standards and code in a way you think is best.

Gold plating code with the best quality standards takes LLMs seconds whereas it would take you days doing it by hand.

The current AI tools extremely good at telling you about how an existing system works. You don't need that one super knowledgeable person anymore.

With the right MCPs or additional context you can have the tools go read PRs or the last 10 tickets that impacted the system and even go out and read cloud configuration or log files to tell you about problems.

The concept of a "bus factor" is a relic of the past.

Because it's such a weasel "just asking questions" thing to do.

If you had a concern about the material costs of renewables you should know what they are and if you wanted to have a good faith discussion, you'd also be able to compare against legacy energy material costs.

I'd disagree the fervor is religious.

I think it's more frustration. Pointing out there is a maintenance cost to infrastructure is silly and doesn't add to the discussion.

We all know materials have to be shaped into machines to extract energy.

I'm not sure what you're trying to say here. Canada can be just as corrupt.

Do you agree or disagree you provided a link to a fitness influencer's website as "evidence?"

Yes the workflow has shifted.

I've handled the sloppiest slop with llms and turned the worst code into error free modern and tested code in a fraction of the time it used to take me.

People aren't worried about cost because $1k in credits to get 6 months of work done is a no brainer.

A year from not semi-autonomous llms will produce entire applications while we sleep. We'll all be running multi-agents and basically write specs and md files all day.