(2025-06-14) Coding Agents Have Crossed A Chasm Flurries Of Latent Creativity

David Singleton: Coding agents have crossed a chasm. If I imagine a ladder of our evolving relationship with coding agents, we’ve climbed to a new rung. We’ve moved from “smarter autocomplete” and “over the shoulder helper” to genuine “delegate-to” relationships - they’re like eager and determined interns.

The journey so far

I’ve really enjoyed using Claude and ChatGPT directly to help me code faster over the past couple of years. They’re fantastic for those moments when you’re staring at an error message that makes no sense, or trying to understand some gnarly piece of library code, or just want to sanity-check an approach. Having a conversation with an AI has become as natural as reaching for Stack Overflow used to be

Cursor, as a human augmentation system, has made a remarkable impact. The inline suggestions and contextual understanding fundamentally changed how I write code. I’m definitely never going back to coding without an assistant

while these human-in-the-loop tools were transformative, the fully autonomous experiences just weren’t close to good enough until recently.

The autonomous revolution, or “this time it really works!”

Now Claude Code and OpenAI Codex are routinely completing whole tasks for me, and it’s genuinely changed everything.

For personal tools, I’ve completely shifted my approach. I don’t even look at the code anymore - I describe what I want to Claude Code, test the result, make some minor tweaks with the AI and if it’s not good enough, I start over with a slightly different initial prompt.

This has unlocked a level of creative freedom where I can build small utilities and experiments without the usual friction of implementation details

For work, I increasingly give small bugs directly to Codex. It can handle simple ones completely, but even for complex issues, it makes a reasonable start. Since it runs in a fully encapsulated environment, it actually takes a bunch of the schlep out of making branches and PRs too.

For code review, we’re finding Claude Code’s GitHub Actions integration remarkably useful.

The frontier models have dramatically improved in their ability to assist beyond simple scenarios. They no longer simply paraphrase docs and SO posts, but feel like they can reason when given the right prompts and context

I had an experience last Friday that illustrates this pretty clearly. It was a moment where Claude genuinely helped me solve something I’d been banging my head against.

We had a subtle issue in one of our OAuth integrations

Instead of diving straight into more code analysis, I tried a different approach. I asked Claude to read through our OAuth implementation and create an ASCII sequence diagram of the entire flow. This turned out to be the key insight. The diagram mapped out every interaction. Having a visual representation immediately revealed the complex timing dependencies that weren’t obvious from reading the code linearly. More importantly, it gave Claude the context it needed to reason about the problem systematically instead of just throwing generic debugging suggestions at me. (notation)

With the sequence diagram as context, Claude spotted the issue: a state dependency race condition.

The real point here isn’t the sequence diagram itself - though do try it if you find yourself in a similar bind - it is the power of helping the model have the right context to actually reason about your problem. This feels like a new kind of programming. What can I say to the model and get it to “think” about that will move us towards our shared goal?

In another recent session, I was trying to fix a frontend problem (some content wouldn’t scroll) and couldn’t figure out where I was missing the correct CSS incantation. Cursor’s Agent mode couldn’t spot it either. I used Chrome dev tools to copy the entire rendered HTML DOM out of the browser, put that in the chat with Claude, and it immediately pinpointed exactly where I was missing an overflow: scroll.

For complex problems, the bottleneck isn’t the AI’s capability to spot issues - it’s our ability to frame the problem in a way that enables their reasoning. This feels like a fundamentally new skill we’re all learning.

All that said, this transition isn’t without significant pitfalls. The biggest one, which I’m still learning to navigate, is what a friend recently described to me as the “mirror effect” – these tools amplify both your strengths and your weaknesses as a developer

These tools work best when you already have enough knowledge to be a good editor.

Addressing the skeptics

“The agents aren’t actually smart, you just know how to use them” - This is partially true and misses the point. Yes, knowing how to prompt effectively matters enormously (the sequence diagram story is a perfect example). But that’s like saying “compilers aren’t smart, you just know how to write code.” The tool’s capability and the user’s skill compound each other.

“We’re entering an era of untrustable code everywhere” - This assumes AI-generated code is inherently less trustworthy than human-written code, which isn’t obviously true. Inexperienced human programmers sometimes write terrible, buggy code too. The real question is whether the combination of AI generation + human review produces better outcomes than human-only development. (cyborg)

“There will be nothing left for us to do” - I’m not seeing this at all. If anything, automating away the mechanical parts of programming frees me up to focus on the interesting problems: architecture, user experience, business logic, performance optimization. only true until staffing drops?

Looking forward

The transformation has been remarkable. We’ve moved beyond AI coding tools being helpful supplements to essential parts of the development workflow. They’re not replacing human judgment - I still design, and make all the critical decisions about what to do - but they’re automating away so much of the mechanical work that I can focus on the problems that actually matter.