Hacker Newsnew | past | comments | ask | show | jobs | submit | Garlef's commentslogin

> but a few generations back

Out of interest: Was this still before CoT/thinking-mode became the norm?


> A vibe coder is someone who wants to test an idea by generating software as a prototype. A software engineer is someone who thinks about the entire software development lifecycle.

I don't think it's such a simple dichotomy; And dismissing the possibilites of agentic coding as inherently non-SWE is rather short-sighted: You CAN use agents as a software engineering tool.

It's just that it's often misaligned with the processes we're used to. But that does not mean that LLM-agents a bad tool.


> dismissing the possibilites of agentic coding as inherently non-SWE is rather short-sighted

The author does not. I recommend reading the whole article, IMO it shows rare (but growing) maturity about software development during this current age of AI tools (I mean in terms of practical day to day use, eg. ignoring (like everybody in tech) the environmental costs). But you might have been misled by how many people have adopted “vibe coding” to mean any use of ai in software dev.

From the article:

> A vibe coder gives the model a goal, but a software engineer gives the model a bounded task. The bounded task is where the engineering happens. Use this interface. Do not touch this layer. And so on. A good prompt is not magic here. It is usually evidence that the engineer already understands the boundary.


To comment on the two sibling responses to my post here in parallel.

I think it gives very valuable insights to tackle the question: "What if we wanted to apply 'vibe-coding' as an SWE technique?"

There's a lot of interesting nuance to cover:

- How can we ensure that agents produce the codebases we want?

- How can we reduce the cognitive burden of code review?

- Do we actually need to review everything?

- How can we safely vibe-code in regulated environments (ISO 27001)?

- How can we use vibe-coding to safely evolve production-grade systems?

- ... etc, etc

I find this approach much more interesting than dismissing vibe-coding as non-SWE.


We really do need to review everything. Whether that's actually being done in practice with enough competence was already a significant risk before LLMs.

LLMs today can reduce cognitive load, but only when it gets it right (about half of the time). They're better than nothing if you don't have anyone else to help review. They still have a very long way to go compared to two or more human reviewers that know the project well.

I don't have answers for the other questions. They seem irresponsible, not because "vibe code bad", but because there should already be very restrictive templates in place for production and regulated environments. Wanting to vibe anything in there implies those environments are already broken enough to allow shenanigans.


From the article:

> The difference is where the responsibility starts and where it ends.

I think you're missing the point. The post is agreeing with you about using the right tool for the job.

When there's a responsibility to fully understand, demonstrate, and discuss the code at length with various stakeholders, using an LLM can get in the way. There's nobody stopping you from hammering a screw. It's just... cringe.


It's also not a "two-pizza team" market.

Er... No?

Electricity prices in Germany are lower than last year.

https://www.zeit.de/wirtschaft/energiemonitor-strompreis-gas...


I mean higher than in other countries with less solar energy, like France, which has mostly nuclear.

This seems to be a good question for an the LLM of you choice. I've asked one and after some search:

Wholesale prices:

- Germany ~€0.089/kWh - Factor 2.94 to consumer Price

- France ~€0.061/kWh - Factor 2.92 to consumer price

- Spain. ~€0.065/kWh - Factor 2.82 to consumer price

The reason seems to be that this price is driven by the tech that is used to fill the gaps what demand is high.

And coal/gas make this expensive.

- Germany needs a lot of coal/gas at some times

- France has nuclear so less coal/gas is needed

- Spain just has a lot of renewables and needs way less coal/gas to compensate

So France is better off because of nuclear... But Spain is doing nearly as well with renewables.


The "saves $" value is based on fossil fuels, not nuclear.

"Saving money" in an absolute sense is very different from "saving money compared to fossil fuels". The headline talks about the former.

> What is the point of taking pictures, really?

Ephemeral communication?

It's fun; Gets a group together; They touch for a moment; Look at it together; "Oh my good I look so fat"; ...


Isn't this just (roughly) John Searles Chinese Room argument repackaged?

But didn't even John Searle argue at this level when refuting the "systems response" to his chinese room argument?

Very simplified the refutal goes like this: "It would be silly to attribute consciousness to a room".

Ultimately, Searle is berating people for even arguing inside the very analogy he put up to make a point.

(... my key takeaway is that even very smart people get astonishingly dumb on this topic)


> "It would be silly to attribute consciousness to a room".

And regardless of whether you think that's an interesting rebuttal or not, it's safe to say that people who properly accept anthropomorphism of llms are content to be silly in this way.


Sure; But that's not the point that is argued about here.

(To state it in AI lingo:)

It's not about the best measure for "amount of code".

It's about wether "amount of code" is a good metric to begin with.


> At the slightest touch of the reins, he felt a familiarity that shook him...

Ah... Some good, old, pre-AI journalism slop.

Oh the countless times a universities press release has been turned into four pages describing the smell of coffee some scientist inhales on their way through campus...


Not sure if this is the right abstraction: The recall seems to need a search term.

But would it not be more sensible to assume that the full conversation (+ system parts) CAN inform the recall and some neural network picks the right memory bits?

So my fear would be that something like this, if adapted, drags the development into a local optimum that is hard/impossible to get out of.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: