If you love it, do it. It is not that easy to find a job as before, but if you are good and pro-active, and with passion, money will come... no matter what you actually do.
You have good approaches.
I created a slash commands that I run, and explicitly wrote to be executed with Sonnet. I also compact manually, and try to keep the session short.
But let's look at the big picture. When using a tool, it must make our lives easier and more convenient. To stop troubling our minds with redundant things. Our focus must be on the product and its quality, and features, and don't waste energy on things outside the scope. What's the point of using a product that pushes us to think about redundant things.
The whole point of using Claude Code just disappeared. I am thinking more on tokens, limits, and optimizations, making compromises on the tasks, rather than product vision and requirements.
And this is a pity. Total waste of time and energy
but if you put into perspective what it would cost you a month for a graduate's salary - and you compare that to the max plan - the value for money is still astronomically incomparable
I read it in a report:
AI amplifies. It amplifies the success of the good professionals and amplifies the failures of the bad ones.
In all cases, whole enterprise solution can't be made with pure vibecoding. Specification is needed, a basis of predefined rules, coding styles, security considerations.
> AI amplifies. It amplifies the success of the good professionals and amplifies the failures of the bad ones.
It also worsens the problem in general by making it way, WAY easier for the bad ones to performatively appear good. They'll have the better-sounding promises but if you listen to them you'll crash and burn in a few years. This doesn't even have to be intentional, just someone technically ignorant channeling AI sycophancy while simultaneously playing politics (i.e. promotionmaxxing while delegating ideas to AI) will have the problematic effect.
For development Android can be a nightmare. Especially, if you try to make a long-running app. Each OEM (Original Equipment Manufacturer) like Samsung, Honor, Xiaomi, etc has its way to keep the OS up and running, in good shape, performance and with low battery usage. To do this, they have mechanisms that stop applications that they might think are redundant:
- if you use too much battery - they might kill it;
- if you use too much CPU - they might kill it;
- At night the devices goes to 'doze mode' - they might kill it;
- It the app is not opened for a long time - they might kill it;
Some of the 'optimizations' you can disable/enable. Each device has its own menu and naming. But not all of them. And even if you make all configurations good, at some point it is possible an update of the OS to reset your configurations silently.
I don't know how it is in iOS, but in android, long running apps are not something that is 100% doable.
After I struggle for months with my app, I have my preferences for iOS right now. It might be difficult as well, but at least the manufacturer is only one. ;)
gmail :)
Not kidding, Most of the time, when I want to send something from my device to my laptop, I share it with an email. In case of friends, directly in Viber, and Teams.
Yes. When things get too complex Sonnet misses some things. For example, it creates all the components, but does not link them.
Or it does not go deep enough in the code and misses certain usages and possible regressions. In other words, it does not, pro-actively, search for things that I have forgotten to tell the model about.
This is like saying: nobody can do woodworking with with manual tools anymore these days, because there are machines since 30 years that do woodworking.
Yes, but it's very hard to find quality handmade furniture these days, or even capable carpenters for that matter. I visited a few older relatives recently and realised most of them have really well made 50+ yr old pieces of furniture with detailed, intricate design - which you can't get these days.
And unfortunately the same trend is already being seen in code - just look at the vast amount of utterly rubbish apps going around. Even popular apps like BitWarden are being coded in Javascript and built with Electron, and somehow people think that's acceptable. I was shocked to find out recently that even bitwarden-cli was also coded in Javascript.
And now AI has just compounded the problem exponentially. Just look at the state of Windows 11 for instance, which I'm forced to use at work. Thankfully, Linux and macOS are faring a bit better, but for how long?
Sure, good developers may always exist, but I'm afraid their work will get drowned in a sea of garbage - and we're forced to swim in it.
I fully agree with the garbage. It is extremely difficult to release a product these days. Everybody are trying to vibecode something, without any knowledge of basic software development, validation, reviews, specifications. Even if there is something good, and written with focus on the details, it just can't popup and be seen, because the overproduction of software.
Also, changing a job is two-side process. they need to like you and you need to like them. If you find that too many developers are going out, too many job offers from their side, that might mean that the company is toxic. Stable good companies, don't have a lot of job offers. They are not so aggressive searching for people ;)
Always ask why they hire, try to find out why people leave.
I don't know about the medicine. I have not been in any medicine related project, so far.
Regarding the banks, they can't use AI. This is a big security risk for them. They need to keep really, really high level of confidentiality. They need to cover all kind of audits: internal, government, external, etc. No audit will pass, if any of the documentation and implementation go to the cloud.
Highly regulated!
I guess, if the medicine follows the same high level of confidentiality, AI won't be used there as well.
No AI, no push to use it -> normal expectations of time and effort ;)
reply