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

The Last Solo Programmers

cacm.acm.org

Post reply on HN
Print view View original

11–19 of 19 posts

Re: The Last Solo Programmers

#11

Post by CarlosBaquero »

dtagames wrote: post #3

This is an excellent article but starts out with the false dichotomy of vibe vs craft programming. An alternate term is starting to appear, flow coding or agentic coding, where the tool is supervised and direced into coding precise areas under human architectural control, with all the programmer understanding that entails. The author hints at this idea toward the end and likens it to a skilled builder who uses tools…

I do agree that in the end the most productive approach will be a mix. Humans with AI support. My fear is on the possibility that learning to program always with AI support, will limit the quality of learning. Only time will tell.

Re: The Last Solo Programmers

#12

Post by CarlosBaquero »

brazzy wrote: post #10
NotGMan wrote: post #6

The problem is in the very act of creating a false dichotomy of "vibe coder" vs "crafstman": the two extremes exist only in marketing/stupid blogger mentality. The future programmer will have to use both until true AGI is created. You cannot prompt yourself out of difficult scenarious without understanding the underlying mechanisms of the problem/solution. The trivial prompting as in "it's not working for test X, fix…

The real question is: how will programmers who start out learning to program with AI doing all the straightforward, clearly delineated and specified tasks for them, be able to make the jump to steering and overseeing AI when it struggles with more complex tasks?

Exactly, that is the one million dollar question.

Re: The Last Solo Programmers

#13

Post by Terr_ »

markus_zhang wrote: post #2

This is an interesting observation. The difference between code completion, intellisense and AI coding, is that code completion merely gives you the name of a variable or a function, while AI coding thinks for you, which is really bad. That's why I despise Copilot and other AI tools that are embedded in IDEs. I'm OK with ChatGPT because it is in a different window and I'm much inclined to use it -- and when I use it…

Right, there's a difference between replacing your memory versus replacing your goal-setting.

Re: The Last Solo Programmers

#14

Post by cma »

ncr100 wrote: post #9
NotGMan wrote: post #6

The problem is in the very act of creating a false dichotomy of "vibe coder" vs "crafstman": the two extremes exist only in marketing/stupid blogger mentality. The future programmer will have to use both until true AGI is created. You cannot prompt yourself out of difficult scenarious without understanding the underlying mechanisms of the problem/solution. The trivial prompting as in "it's not working for test X, fix…

I don't disagree. And, I'm skeptical agi will usher in human readable, maintainable, and auditable agent-built code. I suppose we'll have to kindly ask the AGI for auditable code.

It's already good at making human written code human readable, not yet refactoring huge complex stuff but helping you read and navigate it.

Re: The Last Solo Programmers

#15

Post by spacephysics »

xeonmc wrote: post #7
dtagames wrote: post #3

This is an excellent article but starts out with the false dichotomy of vibe vs craft programming. An alternate term is starting to appear, flow coding or agentic coding, where the tool is supervised and direced into coding precise areas under human architectural control, with all the programmer understanding that entails. The author hints at this idea toward the end and likens it to a skilled builder who uses tools…

One could also categorize them as slop vs churn programming.

Honest question, do you think this will lead to more work for “hands-on” programmers to fix errors, or this could just be the early stages of agenic coding becoming better and more akin to the best (or close to it) “hands-on” programmer?

Or a different outcome

Re: The Last Solo Programmers

#16

Post by abbadadda »

The way to differentiate oneself is to know and understand the details, and what is actually happening, I think. Applications are messy whether they run on bare metal or in the cloud. If you truly understand what’s going on at a deeper level with the programming language, compiler, and the system architecture (both software engineering architecture and system component architecture) you’ll be a far more valued programmer than one that is just “getting things to work.”

Re: The Last Solo Programmers

#17

Post by johnea »

The reference to Formula 1 not leading to driving decline is somewhat paradoxical.

Formula 1 has a lot of rules regulating what can and can't be done to change the cars. They basically enforce the traditional driving model.

Given this, I almost think this is an example of the opposite of what the author intends it to be. The reason Formula 1 hasn't led to a reduction in driving skill is because they don't allow changes to be made to the driver interface to the car.

Re: The Last Solo Programmers

#18

Post by isaacremuant »

dtagames wrote: post #3

This is an excellent article but starts out with the false dichotomy of vibe vs craft programming. An alternate term is starting to appear, flow coding or agentic coding, where the tool is supervised and direced into coding precise areas under human architectural control, with all the programmer understanding that entails. The author hints at this idea toward the end and likens it to a skilled builder who uses tools…

It's not an excellent article.

It's basic and confuses uses abstractions with not knowing fundamentals.

It goes into all the common places of "AI will replace you if you don't think" and pretends you fundamentally don't reason or think if you interact with an abstraction or AI.

The examples are so rudimentary that I very much suspect this person is not particularly good at software engineering.

People will read this title and comment because doom posting about AI is what people want to do if they're uncertain about "losing value" but it's very low quality.

Re: The Last Solo Programmers

#19

Post by xeonmc »

spacephysics wrote: post #15
xeonmc wrote: post #7

Earlier quoted context omitted.

One could also categorize them as slop vs churn programming.

Honest question, do you think this will lead to more work for “hands-on” programmers to fix errors, or this could just be the early stages of agenic coding becoming better and more akin to the best (or close to it) “hands-on” programmer? Or a different outcome

Market forces will drive the outcomes in different sectors.

In aviation-minded companies, human-reviewed guardrails will always be in place, some may eventually decide to might as well have humans write the whole thing to begin with to keep it end-to-end auditable.

In automotive-minded companies, "chabuduo" is the norm and agentic may be "good enough if it appears to work" and only involve humans when visible crises surface, in which case the most desired programmer are those who can churn.

Post reply on HN