That's what he said. AI is building AI so that's where they are headed.

Most of my devs don't write code, they review it.

I would wager $1m that Anthropic will still have SWEs doing engineering work 3 years from now, if the company is still around.

Yeah. And afaik and hage used AI models, unless you use claude opus 4.5high you don't get good results

If AI can do the full job of a software engineer, then it can review code too.

I use cursor on a daily basis. It is good for a certain use cases. Horribly bad for some other. Read the below one by keeping that in mind! I am not an LLM skeptic.

It is wild that people are ao confident with AI that they're not testing the code at all?

What are we doing as a programmer? Reducing the typing + testing time? Because we have to write the prompt in English and do software design otherwise AI systems write a billion lines of code just to add two numbers.

This hype machine should show tangible outputs, and before anyone says they're entitled to not share their hidden talents then they should stop publishing articles as well.

You can't have your cake and have it too!

You'll see countless posts on LinkedIn about how great LLM is. Nobody goes in depth these days - just superficial posts

Not to mention the fact that juniors can now put the entire problem statement in AI chatbot which spits out _some_ code. The said juniors then don't understand half the code and run the code and raise the PR. They don't get a pat on the back but this raises countless bugs later on. This is much worse as they don't develop skills on their own. They blindly copy from AI.

We use mcp at work. Due to some typo the model ran absolutely random queries on our database most of the cases. We had initially kept ot open ended but after that, we wrote custom tools that took an input, gave an output and that was strictly mentioned in the prompt. Only then did it work fine.

Also since firefox is FOSS and any model has reasonably been trained on the code base of at least Firefox if not also Chromium, it's not a shock that agents are able to generate a similar code!

> other corporations in the space is that we shouldn't jump the gun before a reasonable framework exists to evaluate such open-ended technologies

How else will they raise a Bajillion $ for the next model?

Until I resd this blog I was under the impression that everyone wrote Python/ other files and used Github Actions to just call the scripts!

This way we can test it on local machine before deployment.

Also as other commenters have said - bash is not a good option - Use Python or some other language and write reusabe scripts. If not for this then for the off chance that it'll be migrated to some other cicd platform

People should switch to Linux. I started using Fedora on Cosmic and it is great!

Mint is very similar to Windows UI

I have written a foss python book on github. In the apst 5yrs, the same Acquisition editor from Apreas reached out to me about publishing my book. When he reached out to me for the first time, I was excited. He gave me a format and I expanded my book in their format. Then 6 months later dude emails me that it was rejected and if I could write something else, he recahed out to me and now he made a u turn asking me to write something different blah blah

I said no thanks and moved on.

A few years later, dude sends me the exact same email. I replied saying that get me in writing that you'll publish the book this time because the last time you wasted my 2 3 months.

Publishing is hard. Yess publishing is even harder. Royaltie are dwindling not to mention these days the documentation has improved so much that people learn from that.

My foss books have netted me more $ than if I had signed up with Apress, so not a loss!