Extasia785

Can developers agree on what the best programming language is? The best framework? The best OS?

AI is a diverse technology and will work differently for everyone, just like JS is a really, really bad technology for many, yet widely used.

On top of that it (as coding agent) is brand new, just a few years old. Looking at the history of technology it will probably take a few decades for it to settle into some sort of stability. Which does not mean it does not provide value during this time of exploration, however there is no trodden path leading you there.

I don't agree with many statements in the article. It almost seems like an article from about a year ago, despite it being posted yesterday. Not sure if the author had the idea a long time ago and just took his time to finish it up, but the "vibe-coding" he describes surely isn't the current way of using LLMs in a codebase.

While LLMs are surely used to generate a lot of slop-code and overwhelm (open source) code bases, this surely isn't the only thing they can do. I dislike discussing the potential of a technology exclusively by looking at its negative impact.

LLMs in proper hands don't create code which is "stolen", they also shouldn't create unnecessary code and definitely don't remove any of the ownership of the programmer, at least not any more than using a mighty IDE does.

The problem seems to be in the usage of LLMs. These effects definitely do happen when just releasing an agent on a codebase without any oversight. But they can also largely be mitigated by using frameworks such as Openspec or Spec-Kit, properly designing a spec, plan, granular tasks and manually reviewing all code yourself. The LLM should not be responsible for any creative idea, it should at most verify the practicality against the codebase. When doing that, the entire creative control is in the hands of the programmer and so is the mechanical execution. The LLM is reduced to a very powerful autocomplete with a strict harness around it. Obviously this also doesn't lead to 10x or even 100x improvements in speed like some AI merchants promise, but in my personal experience the speedup is still significant enough to make LLMs a very, very useful technology.

A forklift is "lifting" things, despite using a completely different mechanical process as a human "lifting" things. The only real similarity between these kinds of "lifting" is the end result, something is higher up than it was before.

> but it's really helpful when it comes to fixing your mistakes, allowing you to be successful.

It would be helpful if they'd take a loss as a learning opportunity. But as stated in the original quote they threw a tantrum and accused the opponent of cheating, taking away no lesson to improve the next time around.

This entirely depends on the company culture. I worked in teams where every small decision is in the hand of the PO and I've worked in teams where a software engineer is a respected professional enabled to make their own technical decisions. I found the second option to create higher quality software faster.

Also not sure what you mean by additional effort? Created_at, updated_at or soft-deletes are part of most proper frameworks. In Spring all you need is an annotation, I've been using those in major projects and implementation cost is around a few seconds with so far zero seconds of maintenance effort in years of development. At least those fields are solved problems.

Ukraine has around $1.2 billion and still got 10% tariffs.

A bad analogy doesn't make a good argument. The best analogy for LLMs is probably a librarian on LSD in a giant library. They will point you in a direction if you have a question. Sometimes they will pull up the exact page you need, sometimes they will lead you somewhere completely wrong and confidently hand you a fantasy novel, trying to convince you it's a real science book.

It's completely up to your ability to both find what you need without them and verify the information they give you to evaluate their usefulness. If you put that on a matrix, this makes them useful in the quadrant of information that is both hard to find, but very easy to verify. Which at least in my daily work is a reasonable amount.

> For each problem, our system sampled many candidate submissions and submitted 50 of them based on a test-time selection strategy. Submissions were selected based on performance on the IOI public test cases, model-generated test cases, and a learned scoring function. If we had instead submitted at random, we would have only scored 156 points on average, suggesting that this strategy was worth nearly 60 points under competition constraints.

Did you read the post? OpenAI clearly states that the results are cherry-picked. Just a random query will have far worse results. To get equal results you need to ask the same query dozens of time and then have enough expertise to pick the best one, which might be quite hard for a problem that you have little idea about.

Combine this with the fact that this blog post is a sales pitch with the very best test results out of probably many more benchmarks we will never see and it seems obvious that human experts are still several order of magnitudes ahead.

I've started doing something similar around a year ago, after noticing that I reached basically all goals I set out for myself after school. I was at a point where I felt like I stopped growing as a person and found myself unhappy with my life, yet was seemingly stuck.

What I did was to have a very strong introspection over a few weeks. I thought about each important aspect of my life - social life, family, career, hobbies, health, even my daily structure - and formulated a very specific target for each area. Basically a well thought out fantasy character. This was hard work, it took many nights of thinking and it's honestly a process that never stops, even nowadays I still update that document from time to time.

Once I had a list I was reasonably happy with, I started thinking of the type of person that would reach that goals and what kind of habits they had. And then I started implementing them. The most important part here is a habit of doing stuff. I can not stress enough how important that is, everything else pales in comparison. I recommend reading Atomic Habits and personally follow the "Getting Things Done" system. But once you have written down everything you need to do and actually do it, you have a superpower and the ability to transform every part of your life in a few months. I found that most "hard" things in life are actually quite easy to do, it's just that doing stuff consistently is extremely hard.

I agree with the author, simply telling people about your future self also helps massively. The first time it will feel extremely weird, like talking about a fantasy character. You will talk about some guy you seemingly have nothing in common with and talk about future achievements with absolutely nothing to back it up. But do it 2-3 times and suddenly that future self will feel familiar. Do it some more, take some steps to be that person and suddenly you'll be far more similar to that guy than you could've ever envisioned.

At least for myself this process was the most important thing I've ever done in my life. I've gone from a pretty shy, boring, somewhat depressed and risk-averse guy to moving across the country for an awesome job, restarting my entire social life and solo-travelling across the world. And most importantly, I'm happy now, it feels like I'm finally me and not just the product of my upbringing and surroundings.

I completely agree. I'm always amused by the idea that dating apps have this secret, sophisticated algorithm that gives you dates that are nice but leave you wanting more. Human relationships are hard and I doubt that the best experts in the field could come up with something like that, and it's certainly impossible for an algorithm without any information about the person. I always feel that these complaints come from the frustration of not being able to find the perfect partner, from people who don't even come close to the standard they want in a partner.

In my experience, online dating is a pretty well functioning marketplace. People have a limited amount of time to date, so they'll take the best one they can get. Of course, online dating narrows down the ranking process to superficial information, but I don't think there's a technical solution to that. As a man I've seen both sides of the coin. When I started out with online dating I didn't have good pictures, no good bio, no good writing skills and didn't pay. I went months without a good match and even longer without a date. Then I decided to clean up my profile, highlight my strengths as a potential partner, learned to carry a fun conversation and started paying for the product and suddenly had to reject women, simply because I had too many options for any given night.

Dating apps are just a more extreme form of real dating. Dating always has been a competition, people will choose the best partner they can get. The advantage of the real world is that people often don't have many choices, but the disadvantage of the real world is also that people don't have many choices. Apps get rid of that disadvantage, but also of that advantage.

What's wrong with cancelling Amazon Prime? I did it recently and it took less than a minute. I even had the option to cancel immediately and have them refund my money, even though my yearly subscription was still running for half a year, which AFAIK is not possible for App Store subscriptions. I'm in EU so might be different to US.

Unions in Germany aren't really split up by profession, but by industry. So if you e.g. work in the car or manufacturing industry, there's a good chance that most workers in your company are part of "IG Metall", which is the biggest union in Germany. And that union then negotiates the salary & working conditions for every normal employee, even if you aren't part of the union. So if you ever met a developer from Siemens, Mercedes, BMW, Bosch, etc. they are probably enjoying the benefits of a union.