Philip-J-Fry

A website shouldn't be pinning CPU or GPU. When people run a game they expect some sort of battery drain. People don't expect that some websites will thrash your CPU/GPU like a game.

One LLM prompt can't get you $500K. Why would someone spend $500k instead of just prompting themselves?

Don't you just throw all the washing into the washing machine, wait for it to actually do the work, and then hang it all up afterwards? It's like a 15 minute job max.

Who said they're new? Also, you can encounter new segfaults in a codebase just by executing code paths you haven't seen before.

Segfaults were a thing with the Zig version. Purely based on the fact it's a line by line translation of the Zig code to unsafe Rust, all the Zig code that caused segfaults is going to also cause segfaults in the Rust version. The Rust code won't fix it until they get to the point of refactoring it into idiomatic and memory safe Rust.

As far as I can remember the origins of Bedrock are the original console releases which couldn't ship a JVM. So a whole new codebase was developed, and ultimately it was more performant as it had to run on 7th gen consoles.

That's what half of people's AI developed projects feels like to me. I have colleagues using Openclaw, and having an entire team of agents managing their home infrastructure. And I'm just thinking "why?". They're not developing anything that useful, their homes are already automated via home assistant. It's just agents for agents sake. Outside of my work life, I find very little need to be using AI.

They're just saying that like Suno Music, if you look closely the cracks show. They're not saying the music is AI generated.

That depends entirely on how you're using AI. If you're getting it to do all the hard thinking, then sure using the best model is probably always going to be better. But it's also going to be expensive.

Using cheaper models and using your skills and expertise from the pre-AI era can get you working just as fast. You've gotta be more specific about the work you need doing. It's less "vibes" based, but they're still effective.

Also, Chinese models absolutely are taking off. I used Claude and GPT at work, and then I tried using some Chinese models for personal projects. I am 100% convinced they're like 90% as good for 10% of the cost. But you've basically gotta be a good developer first and know what you want and know when it's giving you shit.

I've went on a similar journey and did just end up going to back SQL.

Mapping database rows to domain objects really isn't that painful and you only do it once. So not a big deal. LLMs actually make this a non-issue now.

I actually realised I like the separation of domain objects and the data layer. It just makes things easier to think about for me. And it means my data layer is completely abstracted from the domain. Makes it easier to implement different storage/caching strategies.

And I also realised, if your hot path is needing to get related/child objects then you should probably just write an optimised query as a prepared statement or a stored procedure. It's rare that you actually have that many different ways you want to access the data.

They are really useful for speed of development though if something is completely greenfield and you don't know the full picture of how data is going to be accessed.

Dunno, it seems like the exact kind of thing Claude would think up if you asked it to subtly alter the system prompt to hide this info.

It's all a losing battle anyway.

I commented on the original post and I still don't understand the point of a "Visual Designer" basically reimplementing Windows XP in the browser. What are you trying to show off?

Also, it seems very buggy with the visuals. I see weird artifacts.

I have one too. He'll say "Claude says this:" and pastes a screenshot of some Claude Code output. Most of the time it's wrong, or makes assumptions that won't hold true. Or it comes up with some overcomplicated solution and I'm like "This is like a 10 line change, right here".

These people just destroy their ability to read and understand the systems they're working with. I actually see it as them making themselves redundant. Because if you can't understand anything without Claude, and Claude doesn't even give the right answers, then what are you worth?

It depends on where you're using AI. If you're working on a project for yourself or in a tiny company. Then sure, writing the code probably was your bottleneck. But at mid to large companies writing code is maybe 50% of the job, and the other 50% is the process around it. All those processes are the bottle neck, no matter how fast you can write the code. And this was a bottleneck I was hitting well before AI.

I am seeing similar things in just regular tooling and development. Things that can be solved deterministically or what would have been a simple CLI 5 years ago are now an LLM integration.

Instead of using the LLM to create deterministic tools, we are using LLMs to replace them. It's completely backwards and I don't know why people (especially high ranking people in my company at least) seem to think that this is the way forward. No, I don't want a whole CI pipeline that is just LLM prompts. Yes it's very easy, but it's expensive, slow and prone to failure in ways you can't even predict.

Same things like using LLMs for the code review process. What would have been a simple linting rule is now a pass with an LLM rather than using the LLM to create the linting rule, which it is absolutely excellent at creating.

Our entire company is basically ran through Jira. Most processes rely on Jira and certain transitions fire of webhooks for automation.

One of the first things we did when we got access to AI was make a Jira MCP. I try not to touch Jira anymore. I get Claude to just create the Jira issues, write comments, create subtasks, link issues together, etc.

I used to dread having to investigate how to implement something and break it down into tasks because the more granular I broke things down, the more Jira issues I had to create to capture each task. Now I can just write everything up in a file and send an LLM to do all the Jira crap.

But you must understand you are a minority. Most people don't do this, they will get something for free and fiercely defend this right to get things for free.

Libraries aren't unethical, because they're just letting you borrow stock of books. There's practical limits on how it scales, and any impatient users might just buy the book. Once you can infinitely duplicate a work, it's not borrowing.

I don't understand why this is a movement that is ethical to get behind.

Someone spends months or years of their life dedicated to writing a book. And people celebrate the fact they can get it for free, justify it by saying it's not free to search or host this content and offer to donate to piracy sites.

Rather than... Just supporting the author and buying their book?

It's different when this is American education and you're effectively being forced to buy books otherwise. I can understand fighting against that. But most stuff on the archive isn't that. It's just plain old piracy.

Yes a PDF or epub doesn't cost money to "print". Yes no one is "losing" money. But this isn't Netflix or Hollywood who still making billions regardless of piracy. Most of these authors are just regular people.

And the whole preservation angle makes sense when the books are no longer for sale. It's hard to argue preservation when you're linking to or hosting these works the second they are available to download. I'd be much more inclined projects that time walled the data, so you could effectively argue it's for preservation.

Yeah, so whatever you're doing to wrap Claude is broken. Because it's breaking the UI.

"It's never bothered me". Cool. But your tool is bugged.

I don't know what you're talking about.

His tool wraps Claude and breaks the TUI. What's so hard to understand?

That's valid critique. What world have I woke up in today?

So why has your tool completely broken the Claude Code UI then?

Can't you see in the gif? It's completely broken. My Claude doesn't look like that. Neither does anyone else's.

I have tried Claude code. It doesn't look like that!

I don't know what the project is. All I see is a TUI that looks completely broken.

Go and use Claude Code right now. Does it look like that? Random underscores all over the page. No it doesn't.

I don't want to offend (it's AI coded anyway :)) but that does not scream "high quality" to me. The headline gif on that repo just paints a terrible picture. It can't draw a box correctly, there's random underscores all over the screen. The UI itself is just incredibly incoherent. I don't even know what I'm looking at.

Like, no it doesn't seem like very high quality work... It just seems like a vibe coded tool.

Edit: yes it's wrapping Claude. It's BREAKING the TUI. Not sure what people aren't getting here...

I don't agree.

I regularly get pieces of work someone product guy has thought up in an afternoon. They only care about the happy path, and sometimes only part of the happy path. I work for a global company that has to abide by rules and regulations in each country we operate in. The product guy thinks up some feature, we implement the feature, then we're told "actually, we legally aren't allowed to do this in 90% of the markets we operate in". Cool, so we add an ability to disable it in those markets. Then they come back "We can do this in some of those markets if it's implemented with [regulatory bureaucracy], so can you do that please".

Then we have to hack away at the solution because the deadline is right around the corner.

This is not software engineering! None of this is related to the software. The job of a software engineer is to take a list of requirements and figure out the way we accomplish those requirements. Requirements gathering is NOT a software engineering problem. Software is implementation, product is behaviour. That's the split. The behaviour of the thing we're building needs to be known before we even try to seriously build it.

If someone just held back for week and did their due diligence, we would been able to architect a solution that is scaleable, extensible, easy to maintain and can make the future easier.

But it's a self fulfilling prophecy. They need all this stuff because it's a vibe coded app where bugs are randomly introduced, the architecture is overcomplicated and sucks, and stuff is just added for the fun of it.

Do existing companies run entire end-to-end product integration tests on every single change they make to a repo to make sure something hasn't broken? No, they just architect things in a way such that a minor change to something can be tested in isolation. And that can be automated, deterministically and efficiently.

Where I work we can release changes to our production site in minutes almost completely autonomously with high confidence with absolutely zero AI agents in the loop. How did we do it? With lessons learned from the past 5 decades of professional software development experience.

Lets not forget what OpenClaw is at it's core. It's a glorified cron scheduler. Why on earth does any of this effort need to exist. It's not that deep, it's not that complex, it's all AI for AI's sake.

With a lot of these AI tools yea, they release very often. But half the features they add aren't even that useful. They just add shit because they can and they introduce bugs and change behaviour all the time.

Opencode has the same problems. They often do multiple releases of that app a day, yet within the span of a week or two I have had to update my config because some random change has altered the behaviour and my permissions broke. Or I've noticed the way the app renders is suddenly different.

Yet, my day to day usage has barely changed since the version I installed last year. It's like everything changes but nothing changes.

So he's spent $20k in one day. There's not a chance in hell he's actually doing productive work with all these tokens.

Grifters gonna grift. What a state of affairs.

I can tell you how that situation comes about.

You start by rejecting those PRs, saying "write more maintainable code, not quick hacks".

Management starts pressuring the original developer "why is it not merged yet, I thought you had it working".

That developer hits back with "well, it failed code review, they want me to refactor it".

Management goes back to the reviewer, "why did you fail this? It meets coding standards right? Pipeline is green".

Reviewer says "Well, yes it technically meets coding standards but it's full of hacks and is not future proof, it will bite us."

Management says "If we coded for tomorrow we'd never get anything done. Don't be so awkward". And then code gets merged.

Then you learn to just let these people go wild. If it hurts in the future you have a nice little "I told you so". But in my experience, management doesn't actually care if it hurts us in the future, it's not their problem. They just say "Well give me bigger estimates if you need to refactor". Fair enough, it's not a big deal but it is a pointless slog of picking up the pieces.

The other way it comes about is when the original developer just isn't really that good of a developer. So you end up in such an endless feedback loop trying to get the code in a good state that you piss everyone off and it's just easier to merge it.

Some hills just aren't worth dying on. And these guys can be exploited for your own advantage if you want to get code merged quickly ;)

Why wouldn't I just `go install` from the git repo? Why is it worth encouraging the use of python tooling for generic application distribution when things like homebrew or chocolatey already exist?

What problems are they? I can't really think of any problems where writing the code was the hard part.

There's plenty of times where I don't know what code to write because I've never used a library before. But it's just a page of documentation away. It's not hard, it's just slow and tedious.