devld

* slop engineering

> You do that for 10.5 years and you reach the center of the milky way

But that would be pretty pointless without taking the time to decelerate :)

Infinity project (game) https://gamedev.net/blogs/entry/2262302-a-retrospective-on-t... started in 2004. It's not the same exact game, but the developer seems to work on something similar: https://www.inovaestudios.com/Battlescape The journal / blog is very interesting btw.

> You can always become better in your field, but becoming a better human is a lot harder.

This sounds so self-gratifying. You could have also written: "I am better than Steve Jobs and I look down on him".

Warning: The site has a Bitcoin miner or some nasty ads that use all CPU.

Wait until Cyber Resilience Act kicks in.

This has been my experience on a recent small project for a client. I took effort to understand and prepare the spec before feeding it to Claude Opus. Yet, the result was slop full of defects, and one that I did not understand well at that. I just did not have a mental model of it. I just thought, there's no way I could ever feel confident about this code, something is missing. It did not take me long to write the important parts myself, from scratch and develop that mental model.

Then I would use Claude to make a small fix, write a unit test (write a unit test, not suggest what they unit test should be) or write some less important UI code. It just felt like old school development, with some assistance. I think we may see a shift back to a "copilot" mode and by the way, I still use GitHub Copilot. The $19 subscription includes $30 worth of credits and the autocomplete in VS code that uses some cheap model is completely free. This autocomplete is very good and I would like the market to focus more on IDE integrations. The agentic thing is either ahead of its time or it will never have time. Time will tell. I think the LLM can only be as good as the training data, so it will always excel at small chunks, but to implement entire projects of which there's such variety, I would question that. And also, how using it to implement entire projects means the developer does not hold the program model in the mind, which leads to more issues long term.

By the way, in this way of working, I see no difference between Sonnet and Opus. Sonnet is good enough to use as an aid.

> I just assumed that readonly properties will always be pretty performant in general.

This is also the case for variables. var is faster than const, because for const (and let) the engine must do additional work (related to enforcing block-level scope, if I am not mistaken).

I thought this would be about AI slop.

How well can it run GLM 5.2?

15 square cm box? Wow. Are there similar size, but less powered (and cheaper) workstations? I need a box that can build chromium reasonably fast and I would rather have something portable like this than a PC tower, but this is an overkill at $4k.

Bedrock does not have GLM 5.2 and likely will not for quite some time. It seems like they are doing that on purpose due to pressure from Anthropic. DigitalOcean has it though.

DigitalOcean hosts it.

Or "paying the price" literally. I'm returning after a small break and into new GitHub Copilot prices. A simple question / request / analysis on Sonnet - that will be 29 cents, please. I can't imagine how much it will cost to do actual development with it.

Can you order chromium source if you contributed a few commits?

I think it's very likely. This is the reason why I stay on GitHub Copilot business for the time being as a solo developer. I assume that Microsoft has less incentive than Antrophic to break the business agreement and use data for training or re-sell it to Antrophic. If I was using the heavily discounted subscription plan from Antrophic, I would 100% assume everything is fed to the machine. I'd rather pay whatever the API costs, than give it an exact recipe to build my product.

The human brain is not made for multi-tasking. Multi-tasking will always be a productivity and focus hit. This was the point of the article.

> To me, this is similar to being honest. You don't want to depend on a system or checklist for being honest. It is something you always need, as a policy. Focus is like that. If you want to focus seriously on something, just make it a policy, and don't use all these tricks as crutches.

I found that I need a lot of guardrails and "crutches" as you said to be at peak productivity. Maybe something is wrong with me, or maybe it's the Dunning-Kruger effect.

I think I would trust Amazon more than Antrophic, since they have no models of their own, they have no business collecting your data for training, while Antrophic most certainly does.

I'm seeing this with Costa Coffee and Starbucks. They are both changing to a very cheap, plastic white, bright design. Why? So people spend as little time as possible sitting there, so there's a higher turnover.

That was the best thing about Copilot. It was too good to last.

Reminds me of circa 2021 Chromium bug where opening the dropdown menu on GitHub would crash the entire system on Linux. At some point, it got fixed.

Workspaces solve this problem better. Cmd + 1,2,3,4,5,6,7,8,9,0 It's like having 10 monitors in a single one. Though if I remember right, the switch is inefficient on Mac OS, but there's some workaround to that.

Recently I could not get a dedicated CPU "droplet" in any of the datacenters they have.

> I've been playing with SEO for this website, and I learned that Google prefers human content because (they are not gonna say it) it needs to train, it cannot train on what it has already trained on. Google's crawler is hungry for human content

This is the reason why you can hardly trust AI companies to not train on your code. If you care about privacy, I think it's best to use Antrophic models via a third-party provider like GitHub Copilot (business) or Amazon Bedrock.

> Also, the Open to Work banner has the stink of desperation

It may as well say: "need work, bad"

It sounds like a really crappy deal to a contractor. In the eyes of the client, you are basically a janitor and Claude is like a superstar that built the whole thing, while the truth is reviewing such code is harder than reviewing and quality approving one's own work. I hope it proves out to be uneconomical and we will be just rewriting the vibe code from scratch.

I'm repeating this 3rd time, but, a non-technical client of mine has whipped up an impressive SaaS prototype with tons of features. They still need help with the cleanup, it's all slop, but I was doing many small coding requests for that client. Those gigs will simply disappear.

I just got started using Claude very recently. I have not been in the loop how much better it got. Now it's obvious that no one will write code by hand. I genuinely fear for my ability to make a living as soon as 2 years from now, if not sooner. I figure the only way is to enter the red queen race and ship some good products. This is the positive I see. If I put 30h/week into something, I have productivity of 3 people. If it's a weekend project at 10h/week, I have now what used to be that full week of productivity. The economics of developing products solo have vastly changed for the better.

My non-technical client has totally vibe coded a SaaS prototype with lots of features, way bigger product than OP and it sort of works. They spent like 200 hours on it. I wonder what would have been the time needed to clean it up and approve it is secure. I declined to work on it, as I was not sure if it's even possible or if it would be better to rewrite the entire thing from scratch with better prompts. I was not that sure about it given the cost and the fact that they had a product that sort of worked and I let them go to find someone to clean it up. My reasoning is that if the client took 200h to develop this without stopping to check the code, it would take me 2 - 3 x to rewrite it with AI, but the right way, while the cleanup may be so painful it would be way better value for money to rewrite it from scratch.

O.P.U.S OutProgram U Soon

A non-technical client of mine has built an entire app with a very large feature set with Opus. I declined to work on it to clean it up, I was afraid it would have been impossible and too much risk. I think we are at a level where it can build and auto-correct its mistakes, but the code is still slop and kind of dangerous to put in production. If you care about the most basic security.