I’ve been driving Claude as my primary coding interface the last three months at my job. Other than a different domain, I feel like I could have written this exact article.

The project I’m on started as a vibe-coded prototype that quickly got promoted to a production service we sell.

I’ve had to build the mental model after the fact, while refactoring and ripping out large chunks of nonsense or dead code.

But the product wouldn’t exist without that quick and dirty prototype, and I can use Claude as a goddamned chainsaw to clean up.

On Friday, I finally added a type checker pre-commit hook and fixed the 90 existing errors (properly, no type ignores) in ~2 hours. I tried full-agentic first, and it failed miserably, then I went through error by error with Claude, we tightened up some exiting types, fixed some clunky abstractions, and got a nice, clean result.

AI-assisted coding is amazing, but IMO for production code there’s no substitute for human review and guidance.

They claim the agents reliably generated a week’s worth of dev work for $20 in tokens, then go on to list all the failure modes and debugging they had to do to get it to work, and conclude with “Agents are not ready to autonomously ship every integration end-to-end.”

Generally a good write up that matches my experience (experts can make systems that can guide agents to do useful work, with review), but the first section is pretty misleading.

When a robot can reliably do this work, I think it can reliably do any human job that requires physical ability and judgement.

These same LLMs will then get lost in the intricacies of the maze they created on subsequent tasks, until they are unable to make forward progress without introducing regressions.

You can at this point ask the LLM to rewrite the rat’s nest, and it will likely produce new code that is slightly less horrible but introduces its own crop of new bugs.

All of this is avoidable, if you take the wheel and steer the thing a little. But all the evidence I’ve seen is that it’s not ready for full automation, unless your user base has a high tolerance for bugs.

I understand Anthropic builds Claude Code without looking at the code. And I encounter new bugs, some of them quite obvious and bad, every single day. A Claude process starts at 200MB of RAM and grows from there, for a CLI tool that is just a bundle of file tools glued to a wrapper around an API!

I think they have a rats nest over there, but they’re the only game in town so I have to live with this nonsense.

Everyone thinks LLMs are good at the things they are bad at. In many cases they are still just giving “plausible” code that you don’t have the experience to accurately judge.

I have a lot of frontend app dev experience. Even modern tools (Claude w/Opus 4.6 and a decent Claude.md) will slip in unmaintainable slop in frontend changes. I catch cases multiple times a day in code review.

Not contradicting your broader point. Indeed, I think if you’ve spent years working on any topic, you quickly realize Claude needs human guidance for production quality code in that domain.

Damien Hirst is a more polarizing third contender.

Edit: also Yayoi Kusama

Excited to see glimpses of that future. Context switching sucks and I’d much rather work focused on one task while wielding my coding power tools.

> “We’re not a scam,” he continued. “We’re a married couple trying to do the right thing by people … We are legit, we are real people, we employ sales staff.”

> Australian Tours and Cruises told CNN Tuesday that “the online hate and damage to our business reputation has been absolutely soul-destroying.”

This might just be BS, but at face-value, this is a mom and pop shop that screwed up playing the SEO game and are getting raked over the internet coals.

Your broader point about blame-washing stands though.

I start every new feature w/Claude Code in plan mode. I give it the first step, point it to relevant source files, and tell it to generate a plan. I go catch up on my Slack messages.

I check back in and iterate on the plan until I’m happy, then tell it to implement.

I go to a team meeting.

I come back and review all the code. Anything I don’t 100% understand I ask Gemini to explain. I cross-check with primary sources if it’s important.

I tweak the generated code by hand (faster than talking with the agent), then switch back to plan mode and ask for specific tests. I almost always need to clean up the tests for doing way too much manual setup, despite a lot of Claude.md instructions to the contrary.

In the end, I probably get the work done in 30% less wall-clock time of Claude implementing (counting plan time), but I’m also doing other things while the agent crunches. Maybe 50% speed boost in total productivity? I also learn something new on about a third of features, which is way more than I did before.

Alternatives were literally things like going to Napa or an amusement park or go-karting. Or if you really wanted to watch a movie, the options were all other movies. Why pick the one that digs at the tenets of your shared reality?

And it’s totally appropriate for that message to resonate with my boss, but it’s weird for my boss to make that message the focus of what is ostensibly a corporate team-building event.

Edit: just realized I used a “it’s not just this, it’s that” construction. I swear I’m not an LLM, but maybe their prose is infecting my brain.

Did she just not get it? Or did she get it, and it was some weird flex making us watch it with her? I still don’t know.

I’ll eat a healthy diet, exercise, and live a life without persistent diarrhea. I’ll take statins if/when they are medically necessary, and no sooner.

I know sama says they aren’t trying to train new models, but he’s also a known liar and would definitely try to spin systemic failure.

My biggest problem with the OP implementation is the “place” button can be far from the “pick” button. Why not just leave it on the moving element - change the label from “pick” to “place” and call it a day.

- It has gotten easier to file patents, so more are filed.

- Companies increasingly use patents like weapons/deterrents, so there’s more incentive to file an idea you weren’t planning to use to build your war chest.

I suspect regulatory capture is a big part of the explanation though.

There’s just no reason for this. You have one job: Take my signal and display it. Anything else is just another place for things to go wrong.

Everyone likes a service when it’s subsidized by VC dollars. Until they inevitably start turning the screws.

From the other side, it’s night and day. We can have conversations. He can hear my kids. The TV volume is set to reasonable levels.

Sample size of one, but it’s been a tremendous improvement. A lot of places are closing out the second gens right now for $140. I’d give it a go. It’s a pretty low price of entry for something that could literally be life changing.