From this point it take not much more time to add proper ci/cd suite, rework database models and migrate things with now some comfidence.

It works very well on small isolated projects and new builds where resulting tools are produced insanely faster than before and with not comparable average code quality (ai slop is 100x better here) from customer usual habits and expectations.

It's because this approach raise significantly the quality level so quickly and so cheap that I advocate for it.

It however does not work the same way for large legacy projects to revive. For larger projects the reciepe is almost the same but requires significantly more manual testing on each pass and carefull regression check. But it does work.

Customer is happy, they take back "more" control over their legacy horrors at the cost of some extra loc but properly working code. There is no point to fight against "a bit too much code" in my case

I don't want to speak for those that work in elite very sensitive human responsibilities software domains, but in a lot of place this is a revolution in my opinion.

I am now trying to sweet spot things with 27b model + tubo8 so I guess should have plenty quality context left.

the error I made in my tests is to stop with a working configuration that maximised my hardware use, and missing real deep software tests. The one shot 3D app I generated with previous setup is exactly telling this : I did not try my setup on real software development cases.

So thank you for guidance. I am not new using agentic code, but when it comes to proper setup with deep understanding of real trades off on inferences engines, I need more deep undestanding to make better decisions.

The 27b Q6_K turbo 8 for ~150K context should give me a real improvement on this stack. It's test party time :D

Edit : oops, I also found I cannot edit anymore my bold wrong title :/

This AI generated blog article is a kind of "report" of what and how I did and result exemples.

I hope this can be usefull to some peopole.

Note : I am not much intersted in having success with this article, I mainly want to share what I think is an interesting use of a 5090. I generated the blog page telling AI to be compliant with hn "rules" and remain factual.

It's definitely not perfect, done rather quickly, not properly tested over 265K context. please forgive my lazyness :) . I am just enthousiast right now about what can be done on a 5090.

Comments URL: https://news.ycombinator.com/item?id=48433268

Points: 2

# Comments: 2

This is unperfect because of ressource waste and the underlaying unsolved law compliance of these services. But at least you get job done easily this way.

As many things in life this is compromise, not perfect solution. In between using this simple trick I can spend my time on more interesting things.

I respect anyway the fact that people try to fight against the intrusive AI default communication mindset. In the end, i think this post need to be heard rather than having a solution.

I am mid career now.

High level langages like js or python have a lot of bad design / suboptimal code... as well as some java code in many places.

Some bad java code (it just needs to be a sql select in a loop) can easily perform thousand time worse than a clean python implementation of the same thing.

As said above, once c was high level programing language and still is in some places.

I do not code in python / go / js that much these days, but what made me a not so bad developper is my understanding of computing mechanism (why and how to use memory instead of disk, how to arange code so cpu can use it's cache efficiently...)

As said in many posts, code quality even for vibe coded stuff depends more on what was prompted and how many efforts the PR diff is human readable to get maintainable and efficient softwares at the end of the day.

Yet senior devs often spend more time reviewing code instead of actually writting some. Vibe coding ultimately feels the same for me at the moment.

I still love to write some code by hand, but I start to feel less and less productive with this approach while at the same time feeling I don't really lost my skills to do so.

I think I really feel and effectively am more efficient at delivering thing with appropriate quality level for my customers now that I have agentic coding skills in my belt.

Understand how to do the thing

Do the thing

Write down fresh documentation about the thing

I look for some open / free to use (commercial products) generated sound / music AI generation tool that I can run locally on common consummer hardware. I would like to iterate faster on prototyping apps / games without the hassle of searching / currating / cropping / transcoding audio media content.

I do not always need high quality content and do not want to mind if I forgot update media with copyright issues in my dev workflows before publishing.

Nothing very serious though, I just explore simple game dev at the moment and want to focus on game concepts instead of media content management.

any link / suggestion (it could be a 2 steps cli to search -> download from a free sound / music bank) welcome.

Comments URL: https://news.ycombinator.com/item?id=44768186

Points: 1

# Comments: 0

I did not find other comments like this in this thread.

6% M2 cpu (even single core) is a huge computing budget for such a small feature.

At this point I don't really understand why OP seems happy with this result (sorry).

I think even a naive canvas implementation can really and quite easily cut most of this computing budget.

Also, a pure css animated thing should use mostly gpu in a right DOM implementation. I think some issues remains in this result.

Maybe OP displays it's app on a 240hz external screen which makes browser compute DOM animation at 240 fps requiring slighly more compute in a passive way (4o-mini suggests this, I am not sure browser works like this)

I remember too much of my pentium 1 166Mhz let run entire age of empires 2 game in 1997

Am I just not able to find where it is now? is there good alternatives (I don't find some and I am surprised), Is there some sort of legal issues with such kind of software ?

Thank you for any information about this.

Comments URL: https://news.ycombinator.com/item?id=40017123

Points: 1

# Comments: 0

As some other comments says pc games have way better quality and infinitely less ad / bloat / pay to win shit that is the norm on android (and maybe a large part of ios games). There is also a huge game choice for these platforms that supports very well gamepad controls.

These systems are not perfect as they require a "descent internet connection " and a physical gamepad (imo) to have a decent mobile gaming experience. So it.may not fit the case "I want to play games lost in alaska".

Note however that the required connection has argably quite low expectations like ~3 mbps bandwidth and average and less than 150 ms latency to run smoothly with basic resolution (480p). This can be enough on a phone device standard size.

All of this let you play any pc game / retro gaming with possibly high end game renderings for decent hardware / saas prices. (You run games with with small resolution because it targets a phone screen so hardware can compute extra visual effect for a cool rendering on phone)

I found it very useful since I made it, so I share it here in case someone look for a tool like this.

Comments URL: https://news.ycombinator.com/item?id=35492769

Points: 3

# Comments: 2

I guess google knows this and I wonder what is the intention to display 1M result available and let users reach so few in reality. Is it commercial argument ? I hardly belive this is an error. Does it reveal how maybe very fewer data google indexes / retains to keep result efficiency ? Does it reveal some sort of data management / algorithm mechanics from their search engine ?

Comments URL: https://news.ycombinator.com/item?id=29373454

Points: 2

# Comments: 3

I can elaborate more on my inital question by rephrasing as following : "Does short messages systems (messenger like / sms) in 2020 provide better human communication (more efficent, better comprehension) than legacy long messages systems (emails, letters, books) ?

Rephrasing makes me understand that the question is still way to large as it need a lot of definition ans asumption to hope an simple answer.