Live data from Hacker News

For thirty years I programmed with Phish on, every day

christophermeiklejohn.com

121–130 of 191 posts

Re: For thirty years I programmed with Phish on, every day

#121
post #106
post #20

For me it’s the dead. Most days I’d listen to one or two shows from today in history on relisten.net/today. I’m sysadmin not a dev but I also feel that managing an agent is a fundamentally different feeling than performing admin work like I used to. I used to build bridges out of software. I would learn how they work down to the nuts and bolts, and use them to make robust and occasionally clever solutions for our nee…

I've learnt more, and more quickly, with LLMs than before them. Not syntax, no. Bash and Powershell are syntex. But tradeoffs, concepts, understanding new domains I didn't know about.

It’s more than just syntax for me though, it was learning how to code in general, through bash. I was slowly building those skills and starting to apply those lessons when looking at product code. I could just devote that time to study instead but I’ve always learned by doing in my career. Now LLMSs do the doing.

Re: For thirty years I programmed with Phish on, every day

#122
post #19

Programming with Claude is still engineering. It is like designing a bridge, which remains engineering even when a worker pours the concrete instead of you. In the past we were forced to pour the concrete ourselves. I understand how many of us enjoyed the sound and the smell of the concrete being poured. Myself, I’m happy to never get my hands dirty again, and focus on the actual engineering.

It's like writing code with assistant Einstein who is 4 years old.

LLMs are the stereotypical 'idiot savant'

Re: For thirty years I programmed with Phish on, every day

#123
post #36

Everyone is talking about the agents part. I'm going to praise this post for describing it very clearly that some people, from a young age, don't need phases, growing up, trying things, figuring out, exploring the world, finding themselves. Some people are just born something (engineers, in this case), and they're that something for life. I always have a hard time explaining to "normal people" that such life is not b…

> Some people are just born something (engineers, in this case), and they're that something for life. Yes, and it's very not fun when your identity is being reshaped before your eyes in the matter of a couple years. I wonder how many developers are going through real grief right now, while everybody else, lacking empathy, are just repeating "get a grip, it's just a tool" or "you better adapt or you're done". Well, I…

This is a great reason not to identify too much with your work. I have enjoyed AI because it has reminded me that my real calling is art, and that I should be doing that at 8 pm, not coding

Re: For thirty years I programmed with Phish on, every day

#124
I’ve been finding it difficult to hand things over to an LLM completely, and I wonder if this is part of it. I’ll let it help me organize at the beginning, and then I’ll have it come through and refactor or review, but the crafting part is where I want to spend my time. I love hitting tab but it seems like every time I do, I get this sensation like I’ve sort of time-warped into the future by a few seconds, and I wonder what I’d have written if the LLM hadn’t done it for me. At which point I’ll never know.

Great for generating volumes of output. Less great for going into a flow state and coming out with something that looks like I made it, something that I see my hand in

And yeah, maybe it’s because I never quite get into a flow state when I do it this way. Hmm

Re: For thirty years I programmed with Phish on, every day

#125

I feel his pain. I am more towards the opposite end of the spectrum [1]. I program to get things done. Usually, I don’t like programming. It’s too focused on one thing. Sometimes I like it though, precisely because it’s focused on one thing. But I love the things you can imagine and build with it. So for me, LLMs are amazing because I get to be an idea guy when I want but sometimes I can go deep, also when I want. I’…

> So for me, LLMs are amazing because I get to be an idea guy

Enjoy this while it lasts, because very shortly LLMs are going to be fundamentally better at being the "idea guy" as well.

I had the same feeling reading this article today as I did reading the NYT article about the closing of Butter Ridge dairy farm. All that family wants to do is raise cows, name them, and milk them but it doesn't work as a business anymore because the factory farm machine took the viability away.

I feel the author deeply; this is coming for everyone across most of the economy.

Re: For thirty years I programmed with Phish on, every day

#126

Earlier quoted context omitted.

> Some people are just born something (engineers, in this case), and they're that something for life. Yes, and it's very not fun when your identity is being reshaped before your eyes in the matter of a couple years. I wonder how many developers are going through real grief right now, while everybody else, lacking empathy, are just repeating "get a grip, it's just a tool" or "you better adapt or you're done". Well, I…

This is a great reason not to identify too much with your work. I have enjoyed AI because it has reminded me that my real calling is art, and that I should be doing that at 8 pm, not coding

Not sure if your 'enjoyed AI' is meant literally. I have escaped my existential crisis and found solace in art as well, simply because it's a very human method of self-expression and taking shortcuts to pain, effort and creativity by prompting LLMs is still frowned upon, at least by those that take art seriously.

The only way I can still enjoy programming now is if it's applied to artistic endeavours. I'm done with the soulless, cost-efficient software "engineering" (which by itself is a laughable proposition and a far cry from the high standards of other fields of engineering)

Re: For thirty years I programmed with Phish on, every day

#128

Earlier quoted context omitted.

When ChatGPT came out, I was beyond excited. I had a tool to generate config files, and bounce ideas off of, and help unblock me when I got stupid arcane logs I didn't understand. That didn't feel existentially depressing at all; it was just glorified Google in my mind. When the vibe coding tools like Claude and Codex came along, I got into this kind of dread. I'm sort of required to use them for work (we are "AI-fir…

Can you describe how you work in this higher level? Sounds like scratches a similar itch that traditional programming offers.

Sure; for reference most of what I end up doing is concurrent and distributed systems, so that's more or less what I focus on. I don't know if this stuff translates to other domains.

Basically, when I have an idea for a project, I usually start drawing a diagram for how I think things should work. I usually draw it with draw.io first because it's easy and quick. After that, I usually translate this to Mermaid, primarily just to have a second draft, but also because having a text-based system makes it easy to copy and paste around, and that kind of stuff tends to translates well to state-machine based stuff that most distributed systems tend to morph into.

If what I'm working on is relatively simple, I feed the mermaid code into Claude or Codex, give it some surrounding context text about what I want, and get it to hack away.

For more complicated stuff, especially if I want to be more clever with concurrency, I will take my Mermaid diagram and manually convert it to TLA+. If I get stuck with the TLA+ translation, I will sometimes ask Claude for a bit of help but even then I almost always write 90+% of the TLA+ spec by hand.

After that it's basically the same. I feed the TLA+ spec, and provide context to it as well (e.g. how to translate a manual TLA+ mutex or channel implementation to whatever the language has built in).

Since I focus very heavily on the implementation, Claude and Codex generally don't have a huge issue with doing a one-to-one implementation.

Re: For thirty years I programmed with Phish on, every day

#129
post #19

Programming with Claude is still engineering. It is like designing a bridge, which remains engineering even when a worker pours the concrete instead of you. In the past we were forced to pour the concrete ourselves. I understand how many of us enjoyed the sound and the smell of the concrete being poured. Myself, I’m happy to never get my hands dirty again, and focus on the actual engineering.

Yeah honestly. I could easily architect the thing out but coding it is so boring. I love this new paradigm and sometimes the LLM even suggests a better architecture!

I guess we are not the same.

I would be perfectly fine with this new branch of "software development" if you guys didn't coopt our name and call yourselves programmers and engineers.

Re: For thirty years I programmed with Phish on, every day

#130
post #110

Earlier quoted context omitted.

Prices are not going up. DeepSeek V4 Pro is 5-10x cheaper than Claude 4.7. As some of us have been predicting, model capability had already mostly plateaued, and the Chinese have and will continue to relentlessly push cost down. Chinese models will be used for 95% of things, with nation-native models for security/sovereignity-sensitive workloads. Eventually (5+ years from now), efficiency gains and hardware progress…

I want the frontier on prem to be true but IMO not good enough yet unless async. What started as all-you-can-eat $50 buffet has quietly become a $6k bill, frontier models that don’t ship your codebase to Beijing don’t come cheap anymore.

> I want the frontier on prem to be true

> that don’t ship your codebase to Beijing

DeepSeek is open weight, open source.

Post reply on HN