Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

No Coding Before 10am

michaelxbloch.substack.com

Post reply on HN
Print view View original

51–58 of 58 posts

Re: No Coding Before 10am

#51

Post by kamaal »

walterbell wrote: post #10
swiftcoder wrote: post #4

Earlier quoted context omitted.

I think I finally understand why the LLM craze is like catnip to management types - they think they've found a cheat code to workaround the mythical man-month

https://x.com/a16z/status/2018418113952555445 For my whole life in technology, there was this thing called the Mythical Man Month: nine women cannot have a baby in a month. If you're Google, you can't just put a thousand software engineers on a product and wipe out a startup because you can only... build that product with seven or eight people. Once they've figured it out, they've got that lead. That's not true with…

A women can at times, in extremely rare occasions have twins, or triplets, or quadruplets. In 9 months.

So that only goes some distance and then you face new limitations.

Re: No Coding Before 10am

#52

Post by tjansen »

charcircuit wrote: post #50
tjansen wrote: post #48

Earlier quoted context omitted.

> 10 minute is not the limit for current models. I can have them work for hours on a problem. Admittedly, I have never tried to run it that long. If 10 minutes are not enough, I check what it is doing and tell it to do what it needs to do differently, or what to look at, or offer to run it with debug logs. Recently, I have also had a case where Opus was working on an issue forever, fixing one issue and thereby introd…

Sometimes it doesn't work or it will give up early, but considering these run when I'm not working it is not a big deal. When it does work I would say that it has figured out that hard part of the solution. I may have to do another prompt to clean it up a bit, but it got the hard work out of the way. >or offer to run it with debug logs. Enabling it to add its own debug logs and use a debugger can allow it to do these…

That assumes that it can easily reproduce the issues. But it's not good at interacting with a complex UI like a human user.

Re: No Coding Before 10am

#53

Post by sublinear »

malux85 wrote: post #38
gchadwick wrote: post #29

Anyone else find reading things like this slightly exhausting? I'm very much pro AI for coding there are clearly significant capabilities there but I'm still getting my head around how to best utilise it. Posts like these make it sound like ruthlessly optimizing your workflow letting no possible efficiency go every single day is the only way to work now. This has always been possible and generally not a good idea to…

I know people like this, theres a form of procrastination where they are busy hyperoptimising their todo lists and workflows but getting only a tiny amount of actual work done. It's a form of the disconnected intellect - they can tell you the problem, they can even tell you the solution, but they can't turn that knowledge into action. Convincing themselves that utterly trivial inconveniences are so productivity and o…

I almost agree with you, but with regard to this specific blog I'm not sure I can.

From my perspective, all this energy spent on AI prompting is actually just planning meetings and whiteboarding in disguise, but since all that has the bad reputation of luring devs into power struggles and yak shaving this is the new way.

It's likely where most of their improved productivity is coming from. The people doing the meta-work just need be mature about it to avoid procrastinating.

Re: No Coding Before 10am

#54

Post by OutOfHere »

The spec prompts are typically better off being reviewed iteratively using AI itself, a lot more so than merely by pairing with coworkers. Perhaps a combination is best. The point is that AI reviews of the task spec must never be overlooked prior to its execution.

Also, if your spec is taking too long for the agent to execute, odds are high that it's ambiguous, unsound, unreviewed, underspecified, unmaintainable, or the model is just optimized to waste tokens so as to bill you maximally.

Re: No Coding Before 10am

#55

Post by etamponi »

Defletter wrote: post #45
etamponi wrote: post #40

It blows my mind how these posts seem like everyone is victim of a collective amnesia. Literally every single point in the article was good engineering practice way before AI. So it's either amnesia or simple ignorance. In particular, "No coding before 10am" is worded a bit awkward, as it simply means "think before you write code", which... Does it need an article for saying it?

> Does it need an article for saying it? Not for nothing but The Art of War includes really insightful quotes like "If you do not feed your soldiers, they will die."

Good point. To clarify my stance: what I meant is that the narrative of the article is the following: AI made us change the playbook and so now, because of AI, the playbook is this one. Which is like saying that Sun Tzu wrote the cited line of the Art of War in a second edition, whereas his first version was "completely different".

Re: No Coding Before 10am

#56

Post by motbus3 »

aitchnyu wrote: post #46
motbus3 wrote: post #14

Coding tools are less stable as the code grows for several reasons. Some recent techniques claim to be solving this problem but none reached a release yet. Working with what we have now, this is a recipe for disaster. Agents often lies about the outputs. The shorter the context space they have to manage while the bigger the data already in context makes it prone to lie and deceive. It works ok for small changes on to…

I'm writing my side project as if I can afford only a 70B model in 2028, even if I have VC-subsidised unlimited GLM-5 now. I'm trimming away most of the generated code and generating more tests. Would prefer if 2028 models are concise and generates perfect refactors.

I have semi unlimited budget forAI tools. And doing it purely with Claude code or similar has been in effective.

The architecture is too simple or unmaintainable rubbish. One can say that I don't need to care about that, but after few weeks of work, every small chance needs to read everything which quickly gets expensive to do anything.

Using human code and doing similar tasks is incredibly cheaper and more effective.

I run few simultaneous green field projects and I can evaluate basically any tool I want. And I will say that quality wise, all ones I tried are disappointing.

Re: No Coding Before 10am

#57

Post by TonyBorlini »

This vision of "no coding before 10am" captures an exciting shift—but it also raises important questions about correctness, maintainability, and the enduring role of human judgment in software. I've been reflecting on these ideas (especially the claim that "code is context, not a library" and that you should "review the output, not the code") and wrote a response exploring why craftsmanship, elegance, and deep understanding still matter—even, or especially, in an AI-native workflow:

https://deep.liveblog365.com/en/index-en.html?post=195

The goal isn't to reject AI agents, but to ask: how do we build systems that last—not just ship fast? Would welcome thoughts from this community.

Re: No Coding Before 10am

#58

Post by nnx »

yomismoaqui wrote: post #41
gchadwick wrote: post #29

Anyone else find reading things like this slightly exhausting? I'm very much pro AI for coding there are clearly significant capabilities there but I'm still getting my head around how to best utilise it. Posts like these make it sound like ruthlessly optimizing your workflow letting no possible efficiency go every single day is the only way to work now. This has always been possible and generally not a good idea to…

Don't worry so much about spee. Some people obsess over it and don't realize they are running in the wrong direction.

Why do you think it's "the wrong direction" ?
Post reply on HN