utopman

It's not available for people having a 20€ plan only. Am I just not a good customer with not. enough credits capacities ?

I hope this is not too provocative, but where I work the legacy code is such a spaghetti mess and so actively inefficient (queries in loops of loops and plenty of things like this) that just prompt nowaday llm to "write extensive and menignful tests for this module, then rewrite the module clean mvc small functions , small loc per files, well organized files then make pass tests again" often leads to insanely better ai "sloppy" resulting code, plus free test coverage where nothing existed, users instant satisfaction (software become suddenly responsive in less than a second).

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.

you are absolutely right. my title is very bad. I'll update it to a very less absolute statement. sorry for that.

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 :/

Maybe it is just me, but : these emails are spam. Marking them as spam should be easy in a common email box nowdays. Marking these undesired emails as spam lowers email sender reputation, then finally gives real insight to the spamer soon or later. Meanwhile you have no more emails from them.

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.

This.

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.

Then the thing becomes :

Understand how to do the thing

Do the thing

Write down fresh documentation about the thing

Not sure it is your case but I think I sometimes had to solve many of them when I am in my daily task rush. My hypothesis is that I solve them too fast for "average human resolving duration" recaptcha seems to expect (I think solving it too fast triggers bot fingerprint). More recently when I fall on a recaptcha to solve, I consciently do not rush it and feel have no more to solve more than one anymore. I don't think I have super powers, but as tech guy I do a lot a computing things mechanically.

This.

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

This is my thought of the day about this topic I wanted to share.

It does not seems to appear in comments yet and maybe it is a bit out of context but android devices nowdays streams almost perfectly services like geforce (video hardware acceleration is a basic feature on phones) now and it is relativiely easy to setup a proper moonlight / sunshine as android client / remote home gaming pc to get "on premise cloud gaming" .

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)