Loeffelmann

I also love how with the right system prompt they can pull in tooling for what they currently need via a nix shell

How do you prevent prompt injections?

This is strawmaning the article

Why?

I think I was sold the full agentic coding hype all over the internet. You give it a try and it does write a feature really fast. Impressed you test the boundaries more and more and before you know it this has become your new workflow. Breaking free of this again is harder than you'd think even when you do realize what a mess is generated in the process.

> locally coherent but structurally incoherent

Perfectly summarizes what I hate about AI code. The diff looks fine but if you take a step back its an absolute mess. I mean have you looked at the Claude Code or Openclaw codebases? that is the result of full on vibecoded. A bloated unattainable mess that no one understands.

If you ever work with LLMs you know that they quite frequently give up.

Sometimes it's a

    // TODO: implement logic

or a

"this feature would require extensive logic and changes to the existing codebase".

Sometimes they just declare their work done. Ignoring failing tests and builds.

You can nudge them to keep going but I often feel like, when they behave like this, they are at their limit of what they can achieve.

An AI version of ls and fzf bringing your file system to the AI age

> you can always do C-x C-e in bash/zsh (M-v in Fish).

Thanks I didn't know!

Some one apparently figured it out. The first system message has to include

"You are Claude Code, Anthropic's official CLI for Claude."

https://github.com/link-assistant/agent/pull/63

Lol a formatting error in a change log breaking the entire thing

You can use subscriptions.

I like it but I am not too deep into the whole agentic coding business.

Why do all these AI generated readmes have a directory structure sections it's so redundant because you know I could just run tree

It's mainly about showing how low the odds actually are. I think everyone understands they are low but it's ridiculous how low exactly.

this looks like one of those things where it completely breaks apart if you want to do anything custom or out of line to what is intended by the framework. Causing way more headaches down the line then if you just did it yourself from the start.

It's a Fachhochschule. And yeah that lecture was very unusual it felt like the insane rablings of a techno evangelist who jumped on every hype train in the last 20 years. He said the most important technologies are IoT, Blockchain and AI

I am currently a CS student in germany and our python lecturer told us at the first lesson that "we didn't really need to learn python" because AI was going to take over anyways and we will not be writing any code after we graduate. He then encouraged us to use AI on all assignments he gives us. He even allows us to cheat at the final exam by using LLMs.

I was about to have a word with him after the lecture but when he started talking about how crypto is going to replace fiat any second now I knew he was a lost cause.

I asked around with my fellow students what they thought about them and not one minded that they were essentially enrolled in a "how to proompt" class. When I asked one student that it was all nice and well that you pass the module but isn't the ideal outcome that you actually know the language by the end? He laughed and said "Yeah sure, do you think the same about maths"?

That's the point. With the old models they all failed to produce a wine glass that is completley to the brim full. Because you can't find that a lot in the data they used for training.

How is this different from pyodide[0]?

[0]: https://pyodide.org/en/stable/

This worked on firefox

   const event = new Event("mousedown")

   const pArr = Array.from(document.querySelectorAll("p"))

   function switchSymbol(target) {
     target.dispatchEvent(event);
   }

   function switchUntil(target, until) {
     while (target.innerText !== until) {
       switchSymbol(target);
     }
   }

   for (const p of pArr) {
     switchUntil(p, "")
   }

Change the second argument of switchUntil to the emoji you want. HN doesn't allow emojis

It will never stop being funny to me when NoSQL people need schemas for their schemaless database.

It's probably because they are so close. I would imagine many americans would do the same if their neighbourhood was in walkable distance. I live in Germany and I do the same I go shopping everyday for 10 minutes for the things I need for the day.

ChatGPT translation:

Does he not perhaps also live underground when

The day's harmony will be mute to him,

If he can awaken it with gentle care

In the minds of his [own]

[...]

Only he who leaves no legacy of affections

Has little joy of the urn; and if he looks

After the funeral, he sees his spirit

Wander amidst Acheron's lamented temples,

Or seeks shelter under the vast wings

Of God's forgiveness: but his dust

Leaves to the nettles of deserted soil

Where neither the enamored woman prays,

Nor the solitary passer-by hears the sigh

That Nature sends to us from the tomb.

You can try it out here: https://makereal.tldraw.com/

Zod[1] is probably the closest

1: https://www.npmjs.com/package/zod

1: https://github.com/colinhacks/zod

Features that look easy to implement and are not a big deal can turn out to be massive problems and require a large amount of code to actually pull of. I would, in some cases, count responsiveness to be one of those things. Stuff like that may seem like 5% of the functionality but actually makes up a large chunk of the code. This is why you must always have feature parity if you really want to compare code size.

If you really want to compare code snippet sizes, you must offer the same functionality. Otherwise, the comparison is meaningless.

You did the exact same thing before when you compared the Headless UI combobox with your nue.js implementation. Offering fewer features will result in less code. Shocker.

Besides, I don't really care for these comparisons. If something is 2x longer code but more maintainable, it is 100% worth it. Just because something is short doesn't make it better.

Sure but how would normal css make it so you don't have to use those?

I don't understand why tailwind would force you to write more divs then CSS. How do selectors solve the problem of how many elements you need to use to achieve the same design?

What do you imagine a inner monologue to be like?