It's an interesting new type of brag. It roughly means: "I want you to know how advanced I am at using LLMs, and how AI-first I am. So here is how little time I spent, to prove that I am using LLMs as much as possible, demonstrating that I am ahead of the curve on this new trend"
Interesting project. Website discovery is indeed in a pretty dire spot, definitely a space that needs innovation. An auto-labeled website directory isn't that silly of an idea.
I have a 400 GB sqlite database with samples of rendered root document DOMs I use for ad detection in Marginalia Search I've been meaning to explore similar ideas using.
I have been wanting do do this. The biggest source of domains is certificate transparency logs. Also ICANN zone files. According to some scientific papers these cover 88% of all registered domains. You could crawl dns for CNAME records with all ipv4 IPs by distributing requests across dozens of DNS servers, the internet archive or the common crawl but doing it for the internet archive is a dick move without giving them money
There's about 200 million active domains currently. That's about 66% of all businesses worldwide of which there are around 300 million. Around 100 to 150 million have active webpages
> There's about 200 million active domains currently. That's about 66% of all businesses worldwide of which there are around 300 million. Around 100 to 150 million have active webpages
Where do you get stats on this info? Not refuting your claims but it's interesting data. I would've thought a wider gap in all biz to active websites since some countries run nearly all their biz on whatsapp/telegram/wechat.
I remember 300 million is the number of businesses on Google maps. I forgot how I got that number though. I didn't crawl Google maps. A lot or even most of those businesses run via chat often have no physical presence besides the houses of their owners so houses on Google maps are not counted. There are a lot of businesses on shopping malls and B2B businesses that aren't on Google maps often because they don't know they can add themselves to Google maps.
I did count the number of ICANN domains on their zone files on czds and there are a few services selling pre compiled domain lists that do crawling for marketers (it is forbidden by ICANN to use zone files for marketing) I don't remember how I got the active website count of 100 to 150 million, maybe I interpolated by checking some ICANN domains or there's a domain list service that does it. Domain list services usually say how many domains are active regardless of whether they have a website or not
Of course parked domains add up to the active website count even though they have no relevant content
To be fair they are a supremely interesting problem to hack away at, and one that will meet you where you are.
Almost anyone can put together a basic search engine in a few thousand lines of code, it's just not very hard to make a program that will index a few million documents better than Confluence.
Then, between that first ansatz and a working scalable internet search engine, you have a pile of interesting problems touching every aspect of computer science and computer hardware and networking, enough so that hundreds of people will have gotten PhDs in narrow sub-problems of those problems you'll be facing.
It's great because you can just tackle the stuff you feel comfortable approaching and leave the rest for later.
People don't like this because you move the responsibility of verification to the reader.
Does the program cheat? Does it just query a table is saved in some backend? Maybe, I don't know, you don't know, and since the author only pressed enter once no-one will know until/if someone runs into any issues.
When you can create information for free, and you want people to use this information you need to provide guarantees, proof, and understanding beyond what the autonomous model has done. Otherwise you just move the burden of verification to the reader.
did you edit it? did you fully read everything yourself and take out anything extra that didnt need to be in there like unnecessary comparisons and typical AI idioms? tweak the language to be less dramatic or emphatic about things that do not need emphasis?
AI is a great tool, but it is somewhere between a 3D printer and a CNC machine. it can make something smooth and easy to handle and maybe good enough for personal use but you would want to run it through some Finishing steps before giving its output to someone else. In some cases thats using the output as a mold for a full recreation and other times maybe its just sanding it a bit, smoothing out some rough spots and putting paint on it.
youre right not to care about if something was made by a human or a tool, but the full presentation of the content including editing is part of the content when it comes to a write-up.
I am not offloading anything. I need way more critical thinking than I ever needed before to review solutions proposed by my digital slaves to evaluate whether they are garbage or good.
If you think that having slaves means you don’t need to be a good administrator, then you are sorely mistaken.
It requires more brainpower than it ever did to manage a project the size what used to do a 100 people team. All on your own.
The fact that I am arguing with all of you here and not blindingly follow the narrative should tell you all you need to know about my critical thinking prowess.
- i can add and subtract 7 digit numbers effortlessly now
- i am still working on multiplication and division though but we ll get there slowly
- let me give you an example live
2949745
-
2947648
- my thought process to do this goes like this
- 1st 3 digits are same ignore
9745
-
7648
- 2nd step is to round off 9700 - 7700 = 2000, add 45 to it and it makes 2045 , we are still 52 short, add 50 to it and make it 2095, now add 2 and it becomes 2097
- see? no calculator needed
- i can do this faster than you can type the numbers above inside your beloved calculator
> People are increasingly getting fed up with slops like this -- you can see comments in HN discussions.
Why claim 'people' (plenty of people get value from satisficing) and even try to use 'see comments in HN discussions' as if there is something that actually documents that ie 'we all think it'.
I skimmed it and even skimming it I got value from (what some others here) call 'slop'. (The value was basically it gave me an idea of something I could implement and again I didn't have to study it or even understand everything (or agree) just seeing someone did that made me think about something I might want to do.
I dunno, you'll notice several people here saying that got value from it, despite others not engaging with it at all. If your filter is that you don't engage with anything you don't expect a priori to get value from (based on weak signals), you'll miss a lot.
it's not that it might help or not, it's more like,
"if an AI wrote this, that means I can generate the exact same text (or better) myself, and be _even more_ helped, whenever I'm interested in this topic, by using AI"
having a blog full of ai content is like having a web page that's a list of links to searches for random keywords on google: what's your contribution? picking a topic? is that anything?
That's only if you assume the human didn't have any control over what the AI wrote, and I think that's more and more a very wrong assumption. It's easy to have a lot of control over LLM output, and to use expertise to steer it (non experts steer the LLM in very different directions compared to experts). And the output being raw text, it's also very easy to edit and refactor it to say what needs to be said. Some people are even (unconsciously or not) adopting AI colloquialisms in their own writing. I think it's becoming very unclear where human and AI content begins and ends.
> having a blog full of ai content is like having a web page that's a list of links to searches for random keywords on google
What's any blog? A person just presses a bunch of buttons on a keyboard, is that anything?
I think you dramatically overstate the human contribution, but if it exists, it would be seen by the author sharing their prompts. I can see how that might prove embarrassing, though, if their contribution is minimal, so I can see why so few people do it.
> What's any blog? A person just presses a bunch of buttons on a keyboard, is that anything?
If it's a human writing it, sure: it's a unique contribution by somebody who put forth effort to help others.
If it's just LLM output, then you might as well have a blog posting the results of random math equations from your calculator. Was any significant human effort involved? Odds are no, but "authors" using LLMs are free to prove otherwise by providing their prompts.
Reminds me that AltaVista's servers ran in 4G of RAM (there were famous, at the time, pics of the circuit boards - DEC was rightfully proud of this, 30 years ago) and that a modern AltaVista should run on a decent laptop :-)
I still can't find pics of the boards (other than on ebay :-) but https://seltzerbooks.com/alta.html has quotes like "To get a sense of the relative size of the RAM in AltaVista Search, consider that a typical personal computer today comes with 8 to 16MB of RAM, and the AltaVista Index Servers each have 6GB of RAM—about 500 times more." and "AltaVista shows the practical value of machines that have more than 4 gigabytes of physical main memory." (Dick Sites, DEC SRL) The book is from 1997.
This is actually where I see software going in the short term -- cloud moving to local.
A few years ago, if you wanted translation, you'd use Google Translate. If you wanted to search the web, you'd use Google search.
But for a few gigabytes, you can now install nllb-200-distilled-600M, and get translations for almost any language locally. You can have your computer crawl the web, create abstracts and categorizations for websites, and build search exactly as you want it.
The main limiter now is hard drive space (and to an extent, local compute) -- but right now it feels like the 70s again where the terminal into a remote server turned into building applications locally.
It's more of a pipeline than a back-and-forth. New abilities happen in the cloud first because they require specialized, higher capacity resources and then move towards being local as the resource usage gets optimized.
Outside insane GPU appliances, I really see cloud based things as a lock-in to subscription based offerings. The fallacy of always using the latest code isn't worth never ending subscription fees. I'll install it locally. I'll keep my data locally. I don't need to wait for things to upload/download. If there's an update that feels worthy, I'll purchased and install locally.
Sorry I have a lot of trouble understanding what this is useful for. Like, I am never going to replace it with Google, DuckDuckGo, ChatGPT or even Bing.
It's not for that, sorry, I should have been more specific. It's for people who wanna put in the effort and steer their own crawl to surface their own slice of the web. The article is just a little story of the journey
I was wondering the same thing. I’ve wished for just a big blob of the web to grep and regex through, but I don’t think this is that much easier than using duckduckgo or even google.
thanks. I'm still sorting out pricing. I don't have experience with B2B and am interested in empowering out-of-distribution people, so will likely maintain some free tier + congestion-based auction pricing for non-commercial use.
Thats the fun part, the user just went with happy path. Javascript, captchas, cloudflare protected content did not made to the catalogue. This sort of use case exists in LLM training data a lot which makes it easier. The data gathered by the user is not really practically useful cause there are way too many gotchas when it comes to web scraping and building a catalogue (source: I have done scraping for a particular domain data and had to do at least 10+ iterations to get it >90 right)
despite this limitation, there is still some good stuff out there, and with the priority steering, you can focus compute on what you actually want, fast and cheap.
Check out my latest project! You can fork it, tweak the policy manually or with AI, run the system and watch the data come in! It's engineered to keep a low data footprint, so 500k domains fits into 1GB on disk. If you have local models it's free! You just might not get the best throughput depending on your GPU. My production data is not exposed anywhere yet, and I may never expose it. The point is for you to fork and make your own policy, and thus your own personal search engine! The article covers basic analysis on my data, so it's worth a read if you're interested! A deeper analysis may arrive with V2 if I ever do it
It takes a bit of setup and a huge download, but every time I need a good domain I follow this old post from Derek Sivers. I have Claude de-dupe it and turn it into a searchable database (on my machine), then have it search genres and terms I'm looking for. It's a task Claude is very well-suited to, from the technical implementation to back-and-forth about selections.
[link]: https://sive.rs/com
Note -- if you do this, watch out for requesting access to "all tlds". They send you two emails per TLD -- one for your pending state, and one for your approved/rejected state. I suddenly had 1k+ emails flooding into my inbox, until I found the setting on their website to disable emails.
The author struggled with categorization simply because they did not truly understand k-means clustering, a fundamental concept in this kind of computing science.
> pages classified as “portfolio” or “zine” or “software” push their outbound links way up the priority list, pages classified as “corporate” or “docs” push theirs down.
And just like that, you recreated the internet of the 90s - early 00s. Brilliant!
How do you build a list of domains you want to index ? I see there is a fetcher and a spider in the code but so for I haven't found how to build that list.
Ah, I forgot to mention that anywhere. You have to provide your own. You can start from a small set, like 10 websites you like that have a bit of character, and it will also add any domains it finds from those 10
I was thinking that a search engine that ignores anything with advertising on it would be useful. This has inspired me to give it a go (on the weekend even)
There are all kinds of websites in here lol. There is some gold in here and I'm determined to surface it all. I had to wrap this up without full analysis cos it was dragging on
1. read each site
2. rent a 4090 with https://vast.ai to run vllm
3. let llm model invent its own category and tag names freely
4. save 1KB of metadata each
5. `code is going up as open source` soon (TM)