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

Is it all just vapourware?

kirahowe.com

Post reply on HN
Print view View original

111–120 of 208 posts

Re: Is it all just vapourware?

#111

Post by NoDodgeQuestion »

eddythompson80 wrote: post #77
skrebbel wrote: post #36

Earlier quoted context omitted.

I did but it was followed by "holy shit now I gotta review this +3000 -500 LOC PR full of subtly wrong abstractions, needless diversions and incorrect assumptions". People keep repeating your sentiment here but I simply can't follow, are we even on the same planet? Or did everyone switch to just not caring about maintainability and code quality anymore? Or are your work tasks simply so mindnumbingly, stupidly simple…

You have to have a team of agents with different roles reviewing that for you. An Advocate, a Skeptic, an Architect, a Security Engineer, a Disgruntled User, a Single Mom, a Clueless CTO, etc. each provides their unique prospective on the change. Then you have a Remediator and a Consolidator to address the feedback. Finally a Liquidator in case of a catastrophic failure.

You forgot Boot the Dog who simply wakes up periodically to check if the crypto rugpull is ready

Re: Is it all just vapourware?

#112

Post by weakfish »

eddythompson80 wrote: post #77
skrebbel wrote: post #36

Earlier quoted context omitted.

I did but it was followed by "holy shit now I gotta review this +3000 -500 LOC PR full of subtly wrong abstractions, needless diversions and incorrect assumptions". People keep repeating your sentiment here but I simply can't follow, are we even on the same planet? Or did everyone switch to just not caring about maintainability and code quality anymore? Or are your work tasks simply so mindnumbingly, stupidly simple…

You have to have a team of agents with different roles reviewing that for you. An Advocate, a Skeptic, an Architect, a Security Engineer, a Disgruntled User, a Single Mom, a Clueless CTO, etc. each provides their unique prospective on the change. Then you have a Remediator and a Consolidator to address the feedback. Finally a Liquidator in case of a catastrophic failure.

Ah, Poe’s law… my favorite

Re: Is it all just vapourware?

#113

Post by badlibrarian »

stock_toaster wrote: post #76
badlibrarian wrote: post #53

Earlier quoted context omitted.

I've tried. It's like trying to teach squirrels how to Google. Really, you just have to figure out what works for you. You will be rewarded.

This combination of "no true scotsman" and "you're holding it wrong" is quite amazing to behold. If AI is as good as it being marketed as, you shouldn't even be able to hold it wrong!

Ah, the classic HN "I keep Wikipedia's list of logical fallacies on my bookmark bar" retort.

“No true Scotsman” would require me to redefine “senior developer” to exclude people who disagree with me. I didn’t.

And “you’re holding it wrong” is a strange objection to a tool that, like Git, rewards learning how to use it. The question is whether that learning pays off.

Re: Is it all just vapourware?

#114

Post by gmueckl »

pixelesque wrote: post #88
gmueckl wrote: post #66

Earlier quoted context omitted.

This is still rather basic stuff to be absolutely honest with you.

The tests and notebooks maybe: not the unrolling and re-architecting to use masking SIMD-ification. I used to do SIMD stuff a lot over the last 17 years, and it would have taken me probably a day to do that (convert 7 algorithms, all with support for various wrapping/mirroring/clamping extent-handling, so around 800 raw source file lines of templated C++) to use SIMD - and well. Then it probably would have taken me a…

Sorry, but this is just not a complex or hard task in image processing. Image resizing is a staple algorithm as common as bread and butter.

Re: Is it all just vapourware?

#115

Post by weakfish »

gryfft wrote: post #55

It's strange to me that the voices naysaying agentic coding capabilities seem to be getting louder in recent weeks. I almost wonder if there's a campaign to start suppressing public awareness of where SOTA capabilities really are.

Why is that strange? To me, it’s evidence of growing dissatisfaction with the direction of the field and frustration with being made to deal with the consequences of others bad work

Re: Is it all just vapourware?

#116

Post by Multiplayer »

copperx wrote: post #69
Multiplayer wrote: post #9

YMMV but I think with the SOTA models building a token efficient engineering loop is absolutely doable with (imho) solid development and testing practices. I see no reason to buy a 3rd party system for this either. I'm not in enterprise so don't come at me here - I'm a small shop and I'm not trying to corral 100 devs or whatever. We've got linear boards getting cards pushed and pulled, debated over by multiple models…

> True software factories now exist That statement somehow amazes me. Obviously, LLMs need plenty of steering, but I don't get how a company can be built on that.

Small companies doing consulting certainly could. My use of the term "software factory" really implies a lot of automation in turning out useful tools for internal and external customers.

Re: Is it all just vapourware?

#117

Post by y1n0 »

satvikpendem wrote: post #59

[flagged]

I don't think you really deserved downvotes. Some people are more geared toward evangelizing technology (or evangelizing anything really), and some are not. I'm pretty much in the 'not' camp.

I'll share my experiences and how I do things, but I'm not about to engage in arguments about it. If you don't want to use it, then don't. What I do I care?

Re: Is it all just vapourware?

#118

Post by margalabargala »

d4mi3n wrote: post #54
badlibrarian wrote: post #17

It's August 9, 2026 and if you're a software engineer who hasn't had multiple "holy shit, I can't believe it just did that" moments, it's time to consider a new trade.

I find this to be an incredibly myopic viewpoint. Software engineering is not defined by a single tool or technology, but rather how we design, implement, and maintain processes of value we want to automate or scale. LLMs will certainly be an aide, but assuming adoption of them is required across a whole _field_ ignores whole classes of problems, domains, and constraints the production of software covers. Rather, we…

On the contrary, taken at face value I find the GP comment to be spot on.

They aren't saying LLM adoption is required across 100% of the field. They are pointing out that LLMs have reached an impressively capable state, and someone insufficiently inclined to test new tooling that they still dismiss LLMs as "just fancy autocomplete" is exactly who gets left behind when technology advances.

Two things can be true at the same time, 1) that LLMs are not required across a whole field, and 2) that software engineers unwilling to acknowledge their utility have as much a place in the future as the software engineers of 50 years ago who refused to use a compiler.

Re: Is it all just vapourware?

#119

Post by y1n0 »

weakfish wrote: post #115
gryfft wrote: post #55

It's strange to me that the voices naysaying agentic coding capabilities seem to be getting louder in recent weeks. I almost wonder if there's a campaign to start suppressing public awareness of where SOTA capabilities really are.

Why is that strange? To me, it’s evidence of growing dissatisfaction with the direction of the field and frustration with being made to deal with the consequences of others bad work

It's really just evidence of what group of people are doing submissions at any given time.

Re: Is it all just vapourware?

#120

Post by Multiplayer »

y1n0 wrote: post #107
solomonb wrote: post #23

The churn in this space puts javascript to shame. As an example, its only been a few months and AFAICT no one is even talking about openclaw anymore.

Did that get bought by openai? Lost its rogue cool factor.

Did not get bought by OpenAI. Creator was hired by OpenAI and they sponsor the project with tokens. OpenClaw is a non-profit now.

The problem is really that the promise was so big but the management and implementation was so painful, coupled with non-stop updates, coupled with far too big of an implementation surface.

A classic "lets solve 15 problems at once" situation, but none of them really well.

Post reply on HN