[rootnod3]

Definitely FOMO. I have tried it once or twice and saw absolutely zero value in it. I will stick to writing the code by hand, even if it's "boring" parts. If I have to sit down and review it anyway, I can also go and write it myself.

Especially considering that these 200$ subscriptions are just the start because those companies are still mostly operating at a loss.

It's either going to be higher fees or Ads pushed into the responses. Last I need is my code sprinkled with Ads.

[RobinL]

> saw absolutely zero value in it

At the very least, it can quickly build throwaway productivity enhancing tools.

Some examples from building a small education game: - I needed to record sound clips for a game. I vibe coded a webapp in <15 mins that had a record button, keyboard shortcuts to progress though the list of clips i needed, and outputted all the audio for over 100 separate files in the folder structure and with the file names i needed, and wrote the ffmpeg script to post process the files

- I needed json files for the path of each letter. gemini 3 converted images to json and then codex built me an interactive editor to tidy up the bits gemini go wrong by hand

The quality of the code didn't matter because all i needed was the outputs.

The final games can be found: https://www.robinlinacre.com/letter_constellations https://www.robinlinacre.com/bee_letters/ code: https://github.com/robinL/

[brokencode]

So using something once or twice is plenty to give it a fair shake?

How long did it take to learn how to use your first IDE effectively? Or git? Or basically any other tool that is the bedrock of software engineering.

AI fools people into thinking it should be really easy to get good results because the interface is so natural. And it can be for simple tasks. But for more complex tasks, you need to learn how to use it well.

[kemotep]

So is it strictly necessary to sign up for the 200 a month subscription? Because every time, without fail, the free ChatGPT, Copilot, Gemini, Mistral, Deepseek whatever chatbots, do not write PowerShell faster than I do.

They “type” faster than me, but they do not type out correct PowerShell.

Fake modules, out of date module versions, fake options, fake expectations of object properties. Debugging what they output makes them a significant speed down compared to just, typing and looking up PowerShell commands manually and using the -help and get-help functions in my terminal.

But again, I haven’t forked over money for the versions that cost hundreds of dollars a month. It doesn’t seem worth it, even after 3 years. Unless the paid version is 10 times smarter with significantly less hallucinations the quality doesn’t seem worth the price.

[azuanrb]

Not necessary. I use Claude/Chatgpt ~$20 plan. Then you'll get access to the cli tools, Claude Code and Codex. With web interface, they might hallucinate because they can't verify it. With cli, it can test its own code and keep iterating on it. That's one of the main difference.

[Aurornis]

> So is it strictly necessary to sign up for the 200 a month subscription?

No, the $20/month plans are great for minimal use

> Because every time, without fail, the free ChatGPT, Copilot, Gemini, Mistral, Deepseek whatever chatbots, do not write PowerShell faster than I do.

The exact model matters a lot. It's critical to use the best model available to avoid wasting time.

The free plans generally don't give you the best model available. If they do, they have limited thinking tokens.

ChatGPT won't give you the Codex (programming) model. You have to be in the $20/month plan or a paid trial. I recommend setting it to "High" thinking.

Anthropic won't give you Opus for free, and so on.

You really have to use one of the paid plans or a trial if you want to see the same thing that others are seeing.

[brokencode]

You are exposing your lack of learning how to use the tools.

Tools like GitHub copilot can access the CLI. It can look up commands for you. Whatever you do in the terminal, it can do.

You can encode common instructions and info in AGENTS.md to say how and where to look up this info. You can describe what tools you expect it to use.

There are MCPs to help hook up other sources of context and info the model can use as well.

These are the things you need to learn to make effective use of the technology. It’s not as easy as going to ChatGPT and asking a question. It just isn’t.

Too many people never get past this low level of knowledge, then blame the tool.

[kemotep]

I hate that Microsoft did this but I meant Microsoft 365 Copilot. Not Github Copilot. The Copilot I am talking about does not have those capabilities.

[brokencode]

GitHub Copilot has a free tier as well. The $20/month one gives you much better models though.

All I’m saying is that the vast majority of people who say that AI dev tools don’t work and are a waste of time/money don’t know how and really haven’t even made a serious attempt at learning how to use them.

[3vidence]

To be fair there seems to be a weird dissonance between the marketing (fire your workers because AI can do everything now) and the reality (actually you need to spend time and effort and expertise to setup a good environment for AI tools and monitor them).

So when people just Yolo the ladder they don't get the results they expect.

I'm personally in the middle, chat interface + scripts seems to be the best for my productivity. Agentic stuff feels like a rabbit hole to me.

[kemotep]

Well I am not a dev so I am just using the freely available search assist and chatbots. I am not saying the dev tools don’t work; I am saying the chatbot makes up fake PowerShell commands. If the dev tool version is better it still seems significantly less efficient and more expensive than just running “Get-Help” in the terminal from my perspective.

[andai]

I'm on the $20 plan with Claude. It's worth mentioning that Claude and Codex both support per token billing, if your usage is so light that $20 is not worth it.

But if you use them for more than a few minutes, the tokens start adding up, and the subscriptions are heavily discounted relative to the tokens used.

There are also API-neutral tools like Charm Crush which can be used with any AI provider with API keys, and work reasonably well (for simple tasks at least. If you're doing something bigger you will probably want to use Claude Code).

Although each AI appears to be "tailored" to the company's own coding tools, so you'll probably get better results "holding it right".

That being said, the $3/month Z.ai sub also works great in Claude Code, in my experience. It's a bit slower and dumber than actual Claude, so I just went for the real thing in the end. 60 cents a day is not so bad! That's like, 1/3 of my canned ice coffee... the greater cost is the mental atrophy I am now undergoing ;)

[johnfn]

No, it's not necessary to pay 200/mo.

I haven't had an issue with a hallucination in many months. They are typically a solved problem if you can use some sort of linter / static analysis tool. You tell the agent to run your tool(s) and fix all the errors. I am not familiar with PowerShell at all, but a quick GPT tells me that there is PSScriptAnalyzer, which might be good for this.

That being said, it is possible that PowerShell is too far off the beaten path and LLMs aren't good at it. Try it again with something like TypeScript - you might change your mind.

[8note]

im unconvinced that you can learn to use it well while its moving so quickly.

whatever you learn now is going to be invalid and wasteful in 6 months

[brokencode]

Who cares if it’s better in 6 months if you find it useful today?

And I reject that anything you learn today will be invalid. It’ll be a base of knowledge that will help you understand and adopt new tools.

[drw85]

It can also backfire and sometimes give you absolute made-up nonsense. Or waste your whole day moving in a circle around a problem.

[kibwen]

Good news, if you upgrade to our $300 plan you can avoid all ads, which will instead be injected into the code that you ship to your users.