ChicagoDave

If there is any proof that no one will be writing code, this is it.

I encourage all young developers to focus on information architecture, application architecture, pure logic, domain-driven design, and harness engineering.

I have a team of devs proving a significant increase in velocity while maintaining quality.

But it’s private corporate work so I can only suggest you keep an open mind and actually research the effectiveness of GrnAI in application construction.

These replies are getting exhausting. We’re well-passed generating high quality code using GenAI.

If you think we’re still dealing with hallucinations or fake code, then you’re experiences are about 8 months behind.

We build modular systems with plans. One developer (not agent) with Claude Code executes their portion of the plan and everything else is normal monorepo business.

But it’s not a man-month anymore. It’s like half a day.

And if I break up an application then 9 coders with Claude Code can build that application in an unprecedentedly short period.

I paid for Robokiller and it kills 95% of spam. MalwareBytes works too.

The biggest problem is many of these are scams and they rotate phone numbers so tagging doesn’t work.

The politicians use services which also rotate phone numbers.

I still haven’t found a perfect solution.

And every time I drop links to my repos I get accused of pandering.

My point was made. Use GenAI to write a manual for your DSL and then use GenAI to “compile” every chapter from a dumb context-less state. You can validate your language in a week or two.

As much as I love open source software, I always thought it was naive to believe our capitalist overlords would ever allow it to succeed as intended.

You could infer I created two programming languages or you could infer I tested AI generated constructs in a way only AI could.

I designed Sharpee and generated the code with Claude Code. About six months in I had Claude generate a manual for the language. Then I had this crazy idea of testing the manual with a completely dummy instance of Claude in a VM.

Nothing solidified Sharpee more than “compiling” this manual chapter by chapter.

But even that left gaps. I then designed a true DSL called Chord that compiles to Sharpee and this really ramped up the solidity of Sharpee.

I’ve been using Claude Code to build an open source parser-based interactive fiction authoring platform.

One person has been helping me test it. No one is using it and I may end up being its only author.

I’m totally fine with that.

Yes. That’s why I’m here. Why I built and use and sell DevArch. It’s how a complex programming platform was created in 10 months.

But I’m lying and nothing I say could possibly be true.

Except it is and I have receipts.

Is it okay to automate into higher level tasks?

Right.

This is why those of us that follow DDD principles are successful. We know how to manage complexity whether we’re doing it manually or by using GenAI.

There are plenty of non AI security analysis tools we still use and add review gates for security gaps.

There is a huge misunderstanding about understanding the code. It implies knowledge of the classes, interfaces, and even internal logic.

If you design a modular system and generate code under strict rules, no one needs to know any of those things. We only need to understand the design and the results.

If we miss things, iteration is cheap.

I have evidence you're probably wrong, but open to evidence-based commentary.

If you're just knee-jerk anti-AI, then you probably need to sit down because some of us are taking serious evidence-based paths with GenAI.

If you have real data on guardrail ineffectiveness, that would be excellent material to share.

Also known as harness engineering and is written about by Martin Fowler, RedHat, and many senior graybeard architects. I was at the DDD conference in Denver a few weeks ago and there were discussions about extracting value from GenAI and harnesses were the happy path.

In my own works, I've been using a home grown harness called DevArch for about 10 months.

Visit https://genai.cornelson.net/ if you want a detailed rundown of my experiences.

It’s not just me:

https://martinfowler.com/articles/harness-engineering.html

https://milvus.io/blog/harness-engineering-ai-agents.md

https://devarch.ai/

I personally follow Domain-Driven Design principles and old enough to have designed software through the old Anderson Consulting Method/1 practices.

Some of the results of my practices are documented at https://genai.cornelson.net

Speed replaces pragmatism by allowing design flaws to be refactored N times where in the past we’d design around tech debt.

DDD leads to modularity and smaller bounded contexts has a significantly lower risk of being incorrect and significantly higher ability to refactor quickly.

And no you still have to understand how to construct software. We’re just skipping the coding skills and pushing everyone to be architects.

If you build guardrails on what is generated, verification is done at the same time as generation.

Frank never wrote about AI. Brian invented it whole cloth, enabling the grift of his father’s works.

Software engineering experience might be visualized as a panel with a few dozen buttons and levers. The engineers that are most successful with LLMs are the ones that understand more of that panel.

Microsoft has created trust issues (again) with their AI decisions.

This seems like a nice-to-have, but I’d much rather see Azure 2.0. A ground up rebuild of a cloud that has a modern foundation with networking and security architected natively.

I think there’s a difference in vibe coding and what I call accelerated software construction.

Vibe coding is like a last second weekend trip to Paris.

Accelerated software construction is like planning a four week backpacking trip through Western Europe.

I’m a grey beard so I’m on the far side of “writing code is fun” but I get it. I used to love those ah-ha moments when solving coding problems.

But now I love delivering solutions to the business or creating software that works as I envisioned it and those two things are fun in very different ways.

I was a pretty successful BASIC programmer, starting on DEC PDP-11 RSTS/E BASIC. Line number BASIC was good enough for simple applications, but quickly turned into spaghetti code.

Later, the VAX had BASIC with functions and subroutines and dropped the line numbers and this version of BASIC was significantly better. It was procedural, but you could organize your code into modules, keeping it readable and maintainable.

Eventually the non line number BASIC spread to the PC. Microsoft Professional Development System, then Visual BASIC.

Who said anything about trusting the llm, producing un-maintainable code, or not understanding the processes?

You can guard the the variance, test for quality, and still maintain design requirements.

Sorry. Their office was in the Sears (Willis) Tower.

Side note: I interviewed at Heidrick two weeks after 9/11. Manager said they had several employees quit on the spot. They offered terrible compensation so I passed.

Yeah there’s a recruiting firm that literally hires ex-CEOs, puts them on the bench, then searches for their next “assignment”. They pay these people to golf until they place them.

https://www.heidrick.com/

Just responded to a different thread, but it’s the same comment:

I was just at the Explore DDD conference in Denver and a portion of Friday was sitting at the cafe tables informally discussing the impact of GenAI on software engineering with notable people. Most of these people were deeply concerned that if we lean into using GenAI for “everything” that our collective knowledge will dissipate. I was the vocal contrarian. There are many historical examples of humans obfuscating knowledge to simplify progress. Does anyone solder their own microchips at scale anymore? No. We have highly sophisticated robots and machinery to do that work with extraordinary outcomes. In software engineering, if you remove “coding” as a discipline you’re left with all the other aspects of designing software which I contend can be retargeted in college CS curriculum. The leap isn’t about code reviews. It’s about design reviews and that’s where better outcomes are served regardless of whether GenAI is involved or not. I have a roughly year old codebase at https://github.com/ChicagoDave/sharpee/ that is designed by me, but generated by Claude Code with my own skills and agents as guardrails. I’m fairly certain the code I extract from Claude doesn’t require human review, but the design of the system and its changes are continually reviewed by me. My contention is that we “collectively” are still trying to discern where the AI/human line is and most are still “holding” that line to human interactions. Let it go. Define what part you do need human decisions on and focus on those things.

I was just at the Explore DDD conference in Denver and a portion of Friday was sitting at the cafe tables informally discussing the impact of GenAI on software engineering with notable people.

Most of these people were deeply concerned that if we lean into using GenAI for “everything” that our collective knowledge will dissipate.

I was the vocal contrarian. There are many historical examples of humans obfuscating knowledge to simplify progress.

Does anyone solder their own microchips at scale anymore? No. We have highly sophisticated robots and machinery to do that work with extraordinary outcomes.

In software engineering, if you remove “coding” as a discipline you’re left with all the other aspects of designing software which I contend can be retargeted in college CS curriculum.

The leap isn’t about code reviews. It’s about design reviews and that’s where better outcomes are served regardless of whether GenAI is involved or not.

I have a roughly year old codebase at https://github.com/ChicagoDave/sharpee/ that is designed by me, but generated by Claude Code with my own skills and agents as guardrails. I’m fairly certain the code I extract from Claude doesn’t require human review, but the design of the system and its changes are continually reviewed by me.

My contention is that we “collectively” are still trying to discern where the AI/human line is and most are still “holding” that line to human interactions.

Let it go. Define what part you do need human decisions on and focus on those things.

The second I discovered the plan start hook I hijacked it and replaced the built-in planner with my own. The built-in planner is useless.