That's how I thought semantic versioning worked

I feel like there are a lot of people nowadays that are just pretending to be devs and ship things to prod using LLMs

I've also tried to understand the code that AI writes, but it's often insane and untangling it would slow me down so much that it would nullify the gains in speed that AI brings.

To me, either companies realize they're spending a lot more money to ship crappier code and AI becomes a niche, or we'll just stop looking at code. I don't think there's any other option because I don't see AI getting better at it. It seems to actually be getting worse and more annoying to use.

I think they do it to be able to send you notifications and sell you more flights, but I don't understand why they need to be so anti-user. I try to NOT fly Ryan Air unless there is no other airline available. I'd rather pay twice as much than support their poor and sometimes borderline-criminal business practices.

I also forbid replying with anything besides "yes" or "no" to yes/no answers.

It works, Opus 5 is still super-annoying but this makes it bearable to use.

Seems like normal text to me, I don't think we need to scrutinize every sentence, now. Who cares if they used AI?

Another rule that was really helpful for me was to disallow anything that isn't yes/no for yes/no answers. If I ask "is the DB up?", I don't want it to take 5 minutes studying the schema to tell me if any of the tables need to be optimized or not.

I think that a lot of devs just think they _have_ to do it that way, or they over-optimize too early and build the ultimate system before they even know if anyone will use the app or site.

However, it's absolutely exhausting to use because of the way it communicates.

All the jargon and its weird, over complicated way to phrase simple things makes it almost impossible for me to understand what the hell it's trying to even say half the time.

Cherry on top, the idiotic follow-ups and caveats that are completely useless 99% of the times but reveal major bugs 1% of the times, so you're forced to read them. Absurd.

I've tweaked CLAUDE.md to force it to only responds with TL;DRs and avoid follow-ups, suggestions and next steps at the end unless they can lead to destructive actions or loss of data, but I'm fighting against the system and diluting other instructions.

A huge piece of shit like other models, but that's what they pay me to do and I do it and go home.

It's pretty obvious what they're doing.

Spam has taken over every form of communication, but luckily there are easy ways to stop it.

I use AdGuard as ad blocker, blocks ads as a browser extension and ads on websites and apps as a mobile app. For telemarketers I use Should I Answer, it works GREAT. Never ever receive a single call from a telemarketer, they all get blocked automatically.

It's been mostly gathering requirements, trying to understand why something was getting build and chasing clients to get paid.

Trading is the only way to make money I can think of where you don't have customers/clients and are truly in control of your own destiny.

But of course it's not that easy.