quantadev

Doesn't matter. You could replicate the basic functionality of Hacker News in a single Coding Agent Prompt. Sorry, I'm not wrong.

I've been writing web apps since 1998. Just today I implemented a similar tree view, with ability to create, edit, rename, move files and folders in a TypeScript react web app, and my app that I wrote today is a vastly more sophisticated GUI than Hacker News. lol.

I should've been more clear that my claim was only about the ability to post messages, have them stored in a database, and then have a tree-view that displays and edits the posts. That's 99% of what users do right? That entire functionality could be done by an AI Agent nowadays in about 10 minutes.

Google was just the right idea at the right time. Ranking pages based on how many other pages link to it wasn't a brilliant idea, it was just the most obvious thing to do next. It was an algo that you could basically implement in a weekend. Tons of tech companies are just this. Something done at the right time, that was super easy to implement, by people capable of getting others to try it.

A 'Block User' feature would be nice. We don't have that feature do we? HN is full of trolls who fly just below the radar of what level of rudeness it takes to get kicked off.

I mean you could technically balance a sheet of plywood on your back on a bicycle, but it seems like it would become impractical at any speed above 30mph just due to aerodynamic...uh...lift.

"Worst and First beats Perfect and Last"

     - Every Venture Capitalist Ever.

Hacker News has so little capability, almost any experienced developer using a modern AI Coding Agent could replicate the entire thing in a weekend, and perhaps in a single day.

I'm not saying it's bad, or criticizing anyone. I mean it does what it does, and it works, and people like it. But no one should care what technology they're using because there's just nothing impressive going on from a technical perspective.

Pretty slick! I never had played minecraft before. I never knew how blocks were place down until I ran this page. But it needs to be able to use the mouse to rotate, and mouse-wheel to scale!

Because Cosine Similarity is that powerful.

I'm not claiming Cosine Similarity can do things it can't do. I'm claiming it's useful to find related pages, in a very powerful way, and I'm correct.

Lots of cool information there that's right in my wheelhouse, that I'll be going thru. thanks!

Thought Experiment: Imagine if we had a true "Perma-Web" where something like IPFS was keeping a permanent record of every web page. Then we could have a "Semantic Web" where each webpage maps to a single point (it's Vector Embedding) in higher dimensional space.

This would mean you could do things like:

1) Write a blog post, and then find all other blog posts that were the 'closest to yours' that was ever written.

2) Do basic "Search" in a way that's probably more powerful than even the Google Page-Rank Algo, by being able to look up every web page that exists based on a Cosine Similarity.

It's a shame Web3 didn't really ever "go viral" in a big way, or else we'd be able to do this stuff right now.

Stack Overflow never fixed any bugs either, but a developer with access to S.O. always had a huge productivity boost from using it. So with even a 1% productivity boost that means a big company can fire 1% of developers, and we're seeing that happen already, although for largely political and reputation reasons company management is currently denying that AI is a direct cause of the layoffs.

Only an AGI will ever "replace" developers. Current AI merely boosts us.

We can now build the Semantic Web. All we have to do is create a tiny protocol (as an optional extension to MCP) for how organizations can share their SQL Table Create DDL as a static file that MCP apps can read, to understand data, and then, using the already-existing tools for AI/LLM function calling to SQL, that would become a Semantic Web.

That would fill the missing link that always held back the Semantic Web which was the lack of any incentive for companies to bother to use a standard "Data Type" rather than all proprietary data types. Once we have an MCPQ (MCP with Queries), suddenly there's an incentive for organizations to collaborate at the data structure layer.

Despite that this post/blog about AI has some valid points, the truth of the matter is that a good experienced developer _can_ extract the power out of a Coding Agent to get 6 months worth of work done in 3 weeks, and even do it in a language he's never coded in before. AI just isn't AGI yet, so comparing it to a human developer doesn't make any sense, to me. On the other hand, I'd also say AI Coding Agents are "Superhuman" in their vast knowledge and code-writing abilities. This indeed does sound like a contradiction, but the world is nuanced enough for it not to be a contradiction, but just two things that are true in a nuanced way.

Anyone able to summarize the current 'hold up' with diffusion models? I know exactly how Transformers work, but I'm not a diffusion expert. Diffusion is so much more powerful tho (from what I know) it seems like diffusion would already be beating Transformers. Why isn't it?

If Event Horizons can come in any number of dimensions (with the conventional things we call Black Holes having 2D of space-like degrees of freedom on the EH) that leads to the obvious conjecture that our 3D universe might itself be a 'manifold' (projection) from a higher dimensional 4D space (i.e. we live on a 3D EH). That 4D space might even itself be a projection from a 5D one, and so on. This is extremely similar to Holographic Principle, but very definitely a more generalized theory.

When there's two competing technologies, and they're both solving the same problem, I always go with whatever's more popular, unless there's a compelling reason not to. This is mainly because of community support and having more companies/developers motivated to rapidly solve challenges that come up, and/or fix bugs.

But especially in the AI/LLM era it's even _more_ important to use what's most popular because the LLM will know more about it, and can pull information from vastly more resources, including it's most important "source" of all: The model weights.

The question was never "Is topology a field of mathematics". The question was, is that term most often used to refer to surfaces in general, and the answer to that is still 'yes'.

The most common uses of "topology", whenever used to convey a geometry-related idea, is in the more general sense meaning "surfaces". Only one out of a million times is anyone ever referring to the specific mathematical field of the same name to which you refer.

The word "topology" is _much_ more commonly used as a general synonym for "surfaces" than in any other way.

The word "topology" is quite commonly used in all kinds of books, papers, and technical materials any time they're discussing geometric characteristics of surfaces. The term is probably used 1000000 times more commonly in this more generic way than it's ever used in the strict pedantic way you're asserting that it must.

The word "topology" has a legitimate dictionary definition, that has none of the requirements that you're asserting. I think what you're missing is that it has two definitions.

Yeah in Ask mode, it shows me the code it's proposing, and explains it, and I have to click an icon to get it to merge the change into my code tentatively and then click "Keep" to make it actually merge into the code permanently. I kind of like that workflow a lot, but I guess you're saying Agent Mode just slams the changes into the code. I may or may not like that. Often I pick only, parts of what it's done. Thanks for the tips.

I've come to the same conclusions mentioned in most of that and done most of that already. I was an early-adopter of LLM tech, and have my own coding agent system, written in python. Soon I'm about to port those tools over to MCP so that I can just use VSCode for most everything, and never even need my Gradio Chatbot that I wrote to learn how to write tools, and use tools.

My favorite tool that I've written is one that simply lets me specify named blocks by name, in a prompt, and AI figures out how to use the tool to read each block. A named block is defined like:

# block_begin MyBlock ...lines of code # block_end

So I can just embed those blocks around the code rather change pasting into prompts.

Yeah, I'm still on the fence about how I feel about this. I mean LLMs are going to be potentially more fair, and there wouldn't be office politics and people being treated unfairly by an emotional easily-manipulated human boss.

Then again the office politics might even get WORSE when people try to trick an AI Boss into blaming someone else for a problem they created themselves. Then again the AI will have a superhuman knowledge of who checked in bad code that broke the product, etc. Lots and lots of trade-offs.

I'm still trying to decide what I'm gonna do the first time a company tries to have their AI Bot interview me for a job. Will I accept that offer or reject the interview? I'm undecided. I'll probably refuse.

However I think an AI would maybe be more honest, about how well I do and my super high skill level perhaps, and not simply reject people for being over 50, White, Male, Overqualified, and good looking, as is [or dare I say was] the custom with DEI hiring practices, for the last decade...or two.

I assumed I was using 'Agent mode' but now that you mentioned it, I checked and you're right I've been in 'Ask mode' instead. oops. So thanks for the tip!

I'm looking forward to seeing how Agent Mode is better. Copilot has been such a great experience so far I haven't tried to keep up with every little new feature they add, and I've fallen behind.

I love Copilot in VSCode. I have it set to use Claude most of the time, but it let's you pick your fav LLM, for it to use. I just open the files I'm going to refactor, type into the chat window what I want done, click 'accept' on every code change it recommends in it's answer, causing VSCode to auto-merge the changes into my code. Couldn't possibly be simpler. Then I scrutinize and test. If anything went wrong I just use GitLens to rollback the change, but that's very rare.

Especially now that Copilot supports MCP I can plug in my own custom "Tools" (i.e. Function calling done by the AI Agent), and I have everything I need. Never even bothered trying Cursor or Windsurf, which i'm sure are great too, but _mainly_ since they're just forks of VSCode, as the IDE.

I mean it's theoretically possible a 1500s King might have made that book illegal, because of it's general knowledge. That's a legit point.

Sadly the radio carbon dating disproved two of my far out theories, which was, 1) The book survived from some earlier 'iteration' of life on the planet, where all plants were simply different. or 2) All planets form the same 'kind' of carbon-based life, and this book was sent/delivered to us by another planet.

Sadly, it's probably just someone's form of "art", and not even "real".