This is getting more and more accessible. It's also one of the uses which makes sense for LLMs.

This is nice to see the energy still bubbling in the traditional web. It's still there, next to the big mall pushed by search engines. You just need to know where to look and it's not that hard.

The idea is interesting... Seeing how the search engine space is degrading quickly I'm tempted to try this actually.

There's clearly something tempting about a web index somehow separated from Google. It always felt like a natural monopoly and so a type of public service.
Now that push arrives a tad late so the impacts are unclear. Overall I still think this would be a net positive if there are more web search companies built onto such an index.

I admit I'm more and more tempted to pay for my search service as well. It's unfortunately not FOSS... But it's not like the alternative are better there either anyway.

Nice to see such a project be funded. Let's see how far this will go.

We're still fairly dependent on just two major web indices... time for an index built as a common for everyone to use?

Looks like an interesting new search engine.

If you wonder why information retrieval from natural language texts is a tough domain, here is a short article listing the important things to keep in mind.

A new search engine trying to grow. The approach seems interesting, we'll see where it goes.

This looks like now is the time for smaller search engines to shine. Clearly the dominant ones are not doing a really good job anymore.

When SEO and generated content meet... this isn't pretty. The amount of good content on the web reduced in the past decade, it looks like we're happily crossing another threshold in mediocrity.

Yet another article on how you can do search straight in PostgreSQL. This one goes a bit further in how to put the pieces together though.

Yet another article about Postgres full test search features. This one has the advantage of giving us a glimpse about the other available options. Sometimes you want something typo resistant for instance.

Inaccuracies, contradicting itself, conflating events, misquoting sources... all of that mixed with some correct facts, it's a perfect misinformation spreading machine. This just can't be trusted at this point. Those experiments should be stopped in my opinion, better do proper homeworks first, then relaunch when this can be better trusted.

Could this lead to the open web index we all need? I hope this research will have high impact.

Looks like a somewhat recent alternative in the search engine and document indexing space. Sounds potentially interesting.

A good primer on full-text search features in Postgres. A nice way to get started. This is too often overlooked, you can wait before pulling another dependency like Elasticsearch.