Code is cheap. Show me the talk

by ghostfoxgod on 1/30/2026, 12:05:50 PM

Comments

by: rewilder12

The original phrase "talk is cheap" is generally used to mean "it's easy to say a whole lot of shit and that talk often has no real value." So this cleaver headline is telling me the code has even less value than the talk. That alone betrays a level of ignorance I would expect from the author's work. I go to read the article and it confirmed my suspicion.

1/30/2026, 2:13:20 PM

by: gipp

I see a lot of the same (well thought out) pushback on here whenever these kinds of blind hype articles pop up.But my biggest objection to this "engineering is over" take is one that I don't see much. Maybe this is just my Big Tech glasses, but I feel like for a large, mature product, if you break down the time and effort required to bring a change to production, the actual writing of code is like... ten, maybe twenty percent of it?Sure, you can bring "agents" to bear on other parts of the process to some degree or another. But their value to the design and specification process, or to live experiment, analysis, and iteration, is just dramatically less than in the coding process (which is already overstated). And that's without even getting into communication and coordination across the company, which is typically the real limiting factor, and in which heavy LLM usage almost exclusively makes things worse.Takes like this seem to just have a completely different understanding of what "software development" even means than I do, and I'm not sure how to reconcile it.To be clear, I think these tools absolutely have a place, and I use them where appropriate and often get value out of them. They're part of the field for good, no question. But this take that it's a replacement for engineering, rather than an engineering power tool, consistently feels like it's coming from a perspective that has never worked on supporting a real product with real users.

1/30/2026, 2:14:33 PM

by: ekidd

In January 2026, prototype code is cheap. Shitty production code is cheap. If that's all you need—which is sometimes the case—then go for it.But actually good code, with a consistent global model for what is going on, still won't come from Opus 4.5 or a Markdown plan. It still comes from a human fighting entropy.Getting eyes on the code still matters, whether it's plain old AI slop, or fancy new Opus 4.5 "premium slop." Opus is quite smart, and it does its best.But I've tried seriously using a number of high-profile, vibe-coded projects in the last few weeks. And good grief what unbelievable piles of shit most of them are. I spend 5% of the time using the vibe-coded tool, and 95% of the time trying to uncorrupt my data. I spend plenty of time having Opus try to look at the source to figure out what went wrong in 200,000 lines of vibe-coded Go. And even Opus is like, "This never worked! It's broken! You see, there's a race condition in the daemonization code that causes the daemon to auto-kill itself!"And at that point, I stop caring. If someone can't be bothered to even read the code Opus generates, I can't be bothered to debug their awful software.

1/30/2026, 2:01:11 PM

by: giancarlostoro

AI was never the problem we have been having a downgrade in software in general AI just amplifies how badly you can build software. The real problem is people who just dont care about the craft just pushing out human slop, whether it be because the business goes “we can come back to that dont worry” or what have you. At least with AI me coming back to something is right here and right now, not never or when it causes a production grade issue.

1/30/2026, 2:09:40 PM