bubblebeard

I feel this mostly is a side effect from lack of domain knowledge. Most of the time this has happened to me, it's because I myself did not cleanly know how a problem should be solved to begin with. If you have a clear picture of what you want, approximately what syntax goes where and why, thats really when LLMs shine in my experience.

They aren't proposing to replace git though. They are just attempting to make it simpler for developers to follow changes applied by an LLM in an ergonomic fashion. Not saying it will work well but I'm happy to see someone trying a new approach here.

Super cool! Any plans to release it for Linux? Would love to test it but I have no Mac unfortunately

The more complex the more fragile. The simpler the solution the more robust. This, I feel, is an overall truth to software development. And simpler solutions, as far as I know, are usually the more useful ones.

I've read that privileged ports was created as a trust model, so users connecting to a service using a privileged port would know that service was started by root on that server and therefore could be trusted. I always felt this was a bit wierd though, maybe I was missinformed, or maybe priviliged ports was already a thing and was just leveraged this way?

I can understand that feeling, but remember that just because you have been handed a new powertool you mustn't always use it. Life is not about optimizing everything. It makes redundant work faster, where you fully understand from the outset how to write something, but this just frees you up to learn and explore new things, and work on stuff just for the fun of it, like this.

This made me think and reflect, thank you.

Not so much about language design as how easy it is to take a defensive position on something we are comfortable with when it's challanged. This prohibits growth.

When someone suggests you have been doing something the wrong way or has a new idea, it's usually better to hear them out and take what knowledge you can from them, even if they weren't actually trying to help you.

Anyways, thanks again

Not an expert, but, when you give Claude, or any AI agent a query it will usually need to do research, use various tools, execute commands etc. and all of this accumelates text in the conversation thread. Each subsequent query in a thread submits the entire conversation to the API, potentially consuming an unnecessary amount of tokens. Compression attempts to solve this by removing irrelevant information. For example, the entire output from a CURL query and how the AI thought about it might not be needed, having the resulting outcome might be enough. Since compression is also performed by the API though it may be worth it, or not, it always depends on the situation at hand. This is my understanding of it anyways.

I have the same CPU in my primary system, and if you can afford it, it’s so choice.

A big surprise for me, having owned both a Ryzen gen 1 & 3 previously, was that this time my system posted without me needing to flash my BIOS or play around with various RAM configurations. Felt like magic.

While I cannot see a way to effectively stop companies from collecting data from you (aside from avoiding practically everything), that doesn’t mean we should do nothing.

DuckDuckGo aren’t perfect, but I think they do a lot to all our benefit. Theirs have been my search engine of choice for many years and will continue being so.

Shout outs to their amazing team!

Great article. It think it raises a good point. An important aspect of modern programming languages should be to simplify the syntax, to help developers avoid mistakes.

This reminds me of arguing more than once with JS developers about the dangers of loose typing (especially in the case of JS) and getting the inevitable reply ”I just keep track of my type casting.”.

For example, they retain the right now to brick your console remotely if you go against their usage policies. Which they retain the right to change at will. So, effectively you really do not own that console in any way shape or form. Shame really, used to like Nintendo once.

The author makes a good point but for the wrong reason I think. The fact that companies lock down their software, and hardware (looking at you Apple), is their choice just like it is yours to give them the finger.

However, at least in Sweden, a smart phone is practically mandatory since it has become a means of identification used by banks, police, our IRS counterpart etc. Even our physical mail is slowly being digitalised, and these services practically require you to own a smart phone. You can get by without one, but it’s a real struggle.

Therefore there should be laws requiring more transparency of these devices, in my opinion.

Just one more reason not to buy a Switch 2. Seriously, Nintendo has become worse than Apple when it comes to treating their customers. I own hundreds of Nintendo games and every console they ever made, sometimes in multiples. But when I saw of all the shit they were trying to pull with the Switch 2 I decided I was done with that company for good.

Whenever my logic said one thing and my gut feeling told me different, I used to ignore my gut. This would more often than not cause some sort of backlash I could not possibly have foreseen. Sometimes immediately, sometimes several days later.

A year or so ago I got tired of this, started doing the opposite, and I will never go back.

Feelings overall are underrated.

I wanted to take a look, but I didn’t want to create an account. An open demo might help bring in clients. Could not see any real content about how it works on the front page, just all the potential benefits it brings.

Congratulations on the launch though!

I’m strictly against collecting data from users unless absolutely necessary, and never without their consent.

As for technology stripping us of our humanity, I could not agree less. I think it’s helped us connect better with each other across different countries and cultures, broadening what was for many a fairly narrow view of the world. Technologies like computers and the Internet are also amazing tools for aiding humanity in our creativity and exploration of everything.

And as for the constraints they may place upon you it’s no different then government, economy or religion. They are all constructs designed to control you. Best you can do is realize that and live with it as best you can. That or go hermit I suppose, it’s a valid choice.

While I am a little tired of the majority of all news being on the subject of AI, I think it’s important to remember that it is arguably the biggest thing that’s happened to our industry since the Internet. Considering how many areas it can be applied to, and how many different ways it can be used within those individual areas. There is so much to be explored.

Also, no one is forcing us to read about it. I myself do not read much about it. I prefer to explore how to make use of AI within my field on my own, and occasionally I will read a post or article if it seems interesting enough.

The author has a point. Obsolete tests serves no one, but deleting a test because it will randomly fail is an indication of an unstable process. Maybe there is a race condition, maybe your code has some dependency that is sporadically unavailable. Deleting such tests is just turning a blind eye to the problem. Unstable tests means you either didn’t write that test very well to begin with, or the process you are testing is itself unstable.

I’ve been a developer for 25 years and I both love and hate what AI is doing to our industry.

I use these tools in projects where there is no sensitive information, outside of my own code, with a full understanding that I may well be sharing my IP with unwanted processes. I do what I can to mitigate this, but I’m sure it’s not enough.

For performance I think Claude or ChatGpt are the best, but it varies depending on your use case. Best way to find out is to subscribe to a service that offers you the choice to alternate between them, to figure out which works best for you.

The company where I’m currently employed lets us use Github Copilot, even though this is a horrible idea in context of the sensitive information they deal with, and the small edge this gives their developers.

I use AI to search for information a lot of the time, and when I’m satisfied with my results I usually cross reference them against other sources. AI is great at putting you on the right track, but still not good enough to give you exactly what you needed most of the time.

As for workflow. I usually create a mental model, covering all the code I want in the way I want it. Sort of like making a map. Then I ask the coding agent to write it piece by piece, not all at once. If there is too much to do, it gets confused and the code becomes a mess.

After it completes each piece, I review it, fix potential problems and then move on to the next piece.

Initially, yes. For me, it took the joy out of development. I was at the point of abandoning it but decided to try some different approaches with it. I think it’s here to stay and felt there had to be some way to leverage it without it making me depressed.

The way I’m using it now I figured out through trial and error. I form a mental model of what I want from start to finish. I then break that down into pieces, and use AI (when appropriate) to generate the code for each piece in sequence. This essentially leaves me in power of the entire development process, but the AI helps me produce the syntax much quicker than I could without it.

Yeah, most of my best work comes while I’m out for a run on a local forest track. I try not to think about work while I’m out there, probably that’s why it’s so helpful.

My feelings exactly. Whenever I get one of those days I’ve found I get more done away from my desk. Taking a walk in the forest or doing some household chores can really help you get back on track.

Of course at times it’s just better to admit altogether this isn’t a day meant for work and spend it relaxing instead. Usually, the benefit of that is a really productive day at work the day after too, everybody wins.

I am at a loss for words. This is simply an amazing read. Thank you for supplying me with this information.

I think the author meant, in a general way, it’s better to avoid simultaneous writes from different services, because this is an easy way to introduce race conditions.

Very good article, right on point!

I do wonder about why the author left out testing, documentation and qa tool design though. To my mind, writing a proper phpcs or whatever to ensure everyone on the team writes code in a consistent way is crucial. Without documentation we end up forgetting why we did certain things. And without tests refactors are a nightmare.

Gotta love that spaghetti Golum, this is truly great stuff.

Strange post. It reads in part like an incoherent rant and in part as a well made analysis.

It’s mostly on point though. Although, in recent years I’ve been assigned to manage and plan projects at work, and the skills I’ve learnt from that greatly help to get effective results from an LLM I think.

It’s great to see someone doing something just for the love of doing it. We so often get wrapped up in reaching a goal we forget the journey is what matters most. The curiosity and will to learn new things. I think this project reflects this quite well, and bravo on this amazing achievement. It’s seriously badass.

Had no idea about that, thank you for the suggestion!