rco8786

The reviews (both the contents and total count) are not exactly confidence inducing.

The article talks very directly about abandoning human code reviews. Couple that with a layer of AI agents whose purpose is to produce work for other AI agents, and you've got yourself a very efficient token burning feedback loop.

> Measured, not vibes

Sort of ironic considering that there are a LOT of vibe tells in the copy throughout this page. It's a neat looking project, it's a shame that every other sentence has Claude's fingerprints all over it.

> Populist. If scalding hot water and the risk of a burn do not scare you, buy the Boiler. A kettle for real patriots. Not suitable for herbal teas and other woke beverages. Used by veterans, among others. Made in this country, except for some essential components.

Almost too on the nose

> If you pay attention to what it's doing you can learn so much!

I think your post is fair but it's worth pointing out that learning via watching is much less effective than learning via doing.

> We already collectively produce more software than anyone really wants

You'll need to qualify that statement...

It's a coordination problem. 70 amazingly responsible adults still need to coordinate amongst one another. Ad hoc coordination and communication always breaks down eventually.

Well yes, ideally. But real world codebases aren't clean enough to be used as the example ideal. Styles change over time, there are always code migrations and refactors in flight, legacy code exists, etc. Using specific examples of what you expect the LLM (and humans) to do now is necessary.

> AI is only as good as the person using it

Nailed it.

That said, it couldn't have possibly been that bad if you got it to "acceptable" in 2 weeks.

This is fine for one off tools and I do the same. But building long-lived "professional grade" production software this fails real quickly.

My team is using AI for most of the code, but the human review layer is crucial and unavoidable if you're interested in things like reliability, uptime, controlled feature rollouts, the integrity if your user's data, etc.

Software engineers generate security bugs, Software engineers find them, then Software engineers generate fix, collect salary, profit?

Yea. Modern Ruby is "fast enough", but it's very real that when Ruby was hitting its peak it was dog slow. It's hard to shake those sorts of reputations (similar to the "can't scale" reputation that Rails got because of Twitter)

Nothing to do with AI here, it's about immigration.

I feel confident in saying that I am better at computers than 99.99% of the general population and I have no clue what “SS” or blue USB ports are supposed to indicate.

In the US??

> I am also not sure who Stripe Atlas for.

This was such a weird mention to see in the article. Stripe Atlas is a service that helps new businesses incorporate and onboard onto Stripe/partner services with some startup credits. It's been around forever, has nothing to do with AI, and is generally a very well-respected service.

Ok? I'm just explaining what claude code is, not pontificating about the capabilities of AI.

Claude Code is a tool that uses natural language ai systems. It itself is not a natural language ai system.

If they’re reaching the same results across a variety of the most popular public models, it doesn’t seem like that big a deal to know if it was Opus 4 or Opus 4.5

Yea this feels like saying “if you give them good enough specs they’ll produce the code you want” which reduces to…writing the code yourself. Just with more steps.

GH is ripe for a disruptor right now.

I think they're just saying that data extraction tasks are easy to evaluate because for a given input text/file you can specify the exact structured output you expect from it.

Yea, for the vast, vast majority of workloads just forking separate node process ends up being better than mucking with threads.

> they add, remove, refine, change, fix, and break features constantly at that accelerated pace.

I wonder how much of this is because the maintainers are using OpenCode to vibe the code for OpenCode.

> More taskbar customization, including vertical and top positions:

When did they get rid of that?

Ditto here

Love Hammerspoon

Yes, if you had each programmer rewrite the code from scratch each time you updated the spec.

How is your 2 step process not susceptible to all the exact same pitfalls you listed above?

FWIW modern Rails is fairly magic-free also. They learned. With ActiveJob now part of the framework you get event queues/async processing and whatnot as part of the batteries.

I'm a fanboi, so I am biased, but Rails is still pretty great in 2026 for general business purposes.