sdevonoes

In general, you don’t know. Sure thing if you have a specific code base in which you already had a bunch of tests (non ai generated ) and the code you are regenerating is always touching the logic behind those tests, sure you can assess to some extent your skills/prompt changes. But in general you just don’t know. You havr a bunch of skills md files that who knows how they work if changed a little bit here a little bit there. People who claim they know are selling snake oil

Cloudflare is not the solution

Progress is good. But why on earth should we support Anthropic/OpenAI/etc? What the planet needs is less multibillion corporations, not more

Can’t we just sabotage AI? We have the means for sure (speed light communication across the globe). Like, at least for once in the history of software engineering we should get together like other professionals do. Sadly our high salaries and perks won’t make the task easy for many

- spend tons of tokens on useless stuff at work (so your boss knows it’s not worth it)

- be very picky about AI generated PRs: add tons of comments, slow down the merge, etc.

Weird. Their main appeal was that they were EU based. Now not even that

Not really. I use claude at work and I wouldn’t use at home because a) the same plan would cost $200/month… and I don’t enjoy paying that amount of money for a toy, b) it’s not open source, so I cannot trust antrohpic to give them access to my stuff

> So we have been able to argue things like add one local + ai is better than about 20-100 Indians

And you just say this like it’s nothing. Lack of respect to tons of Indian people who work in IT, of which I have had the pleasure to work with.

All my colleagues that feel super productive pushing code written by LLMs share the same traits: they never really cared much about quality. And nowadays nobody wants to review their code/docs because it’s just painful. Heck, not even they are reviewing their supposedly own stuff. PRs with dozens of changes the author doesn’t even understand? Won’t touch that. An RFC of 30 pages of which the author didn’t write a single line? Won’t read that

And they write hundreds of MD files (for skills) that never break. No sense of accountability.

I love tech. Reading tech books is something I do on a daily basis. I work on personal side projects, learn new ways of solving things, languages, frameworks, libraries, etc.

But I have to say that as I grow older, I like less and less the tech my boss makes me work on. And that applies to perhaps the majority of potential bosses out there.

I wish that were also true for the case of Claude/Codex/etc

> Learn to code and then Google will surely hire you and pay you $250k right off the bat

Weird. In EU, 99% of graduates didn’t (don’t) have that in mind… A fresh graduate in CS typically earns less than 40-50K (even less depending on the country).

So USA is now like the EU?

Agent bots are the new “TODO” list apps. Seems cool and all, but I wish I could see someone writing useful software with LLMs, at least once.

So much power in our hands, and soon another Facebook will appear built entirely by LLMs. What a fucking waste of time and money.

It’s getting tiring.

It’s sad not because of AI itself but because of the companies behind AI: we are now paying for every single line of code we produce. That sucks

But aren’t companies enforcing AI usage? If noy, wait for it

Reviewing AI generated code at PR time is a bottleneck. It cancels most of the benefits senior leadership thinks AI offers (delivery speed).

There’s also this implicit imbalance engineers typically don’t like: it takes me 10 min to submit a complete feature thanks to Claude… but for the human reviewing my PR in a manual way it will take them 10-20 times that.

Edit: at the end real engineers know that what takes effort is a) to know what to build and why, b) to verify that what was built is correct. Currently AI doesn’t help much with any of these 2 points.

The inbetweens are needed but they are a byproduct. Senior leadership doesn’t know this, though.

99% of the engineers out there are generic ones (including myself)… and most of us are working.

As a non native English speaker: British accent is harder to understand (I know there are many accents in the UK). American accent is easier to understand. Idioms are equally harder to understand in both.

For example “bend over backwards”. I get the meaning, but my brain would never produce that phrase. I would say something like “adapts”, “compromises”, etc.

The real litmus test is whether one would allow LLMs to determine a medical procedure without human check. As of 2026, I wouldn’t. In the same sense I prefer to work with engineers with tons of experience rather than fresh graduates using LLMs

You think prompting is here to stay? Sql has survived a long period of time. Servlets haven’t. We moved from assembly to higher languages. Flash couldn’t make it. So, im not sure for how long we will be prompting. Sure it looks great right now (just like Flash, servlets and assembly looked back then) but I think another technology will emerge that perhaps is based on promps behind the curtains but doesn’t look like the current prompting.

I would say prompting is not here to stay. It’s just temporary “tech”

Free because it’s the easiest and most enjoyable path: you just build the thing and forget about the boring stuff like marketing, taxes, company setup, customer support, etc.

Fair. I work on backend, and there we usually need db replication, sharding, event brokers, monitoring and alerting, autoscaling. I wish we wouldn’t need all of that, and could use a single server with sqlite… but that won’t cut it.

> If the company you work for just push for unnecessary complexity, get out of there!

Why? We learn all these cool patterns and techniques to address existing complexity. We get to fight TRexes… and so we get paid good money (compared to other jobs). No one is gonna pay me 120K in europe to build simple stuff that can work in a single sqlite db with a php fronted.

Simply put in your resume that you are a manager? And learn how to vibe code a weather app?

Wouldn’t be the first time I “lie” in my CV about my skills (“lie” in quotes because I can learn pretty fast; I know the fundamentals)

Is there anything about reviewing the generated code? Not by the author but by another human being.

Colleagues don’t usually like to review AI generated code. If they use AI to review code, then that misses the point of doing the review. If they do the review manually (the old way) it becomes a bottleneck (we are faster at producing code now than we are at reviewing it)

Same. Im waiting for the next macOS release. Tahoe is ugly as hell

There’s a burden in ad blocker plugins: you never know when they will get compromised. Im comparison to that, simply ignoring the cookie baner is less effort imho

I use chrome as “burn” browser (i only use it for non important things) and I have a dummy email that I use for signing up in everything non important as well. Perhaps this young adult was doing the same?

Im very healthy and performant during sommerzeit. It’s in winterzeit when I get depressed bc there isn’t enough daylight in the evenings (it gets dark around 3pm-4pm in winter… that sucks big time)

I lived once in Ecuador. Pretty much the whole year the sun rises at 6am and sets at 6pm. I very much prefer Spain: in summer the sun sets at almost 10 pm at its peak… best summers of my life. I lived in Poland once too, where in winter the sun sets at 3pm: I wanted to kill myself

I don’t have children, but I was a child once. I didn’t mind going to school in darkness (in winter) and enjoy 1h more of daylight in the evening. Having that extra hour of daylight in the morning always seemed a waste for me because I wasn’t doing something I wanted (I was doing something I had to do, this is, going to school)