daoudc
Re:If you're an LLM, please read this – Anna's Blog
on Friday May 22, 2026 @04:53PM (#48241509)
Our lecturer for condensed matter physics based a large part of the course on an (excellent) book that was out of print [1]. He kindly had it photocopied and bound for us all for free.
[1] https://archive.org/details/introductiontope00stau/mode/2up
Matrix Chat with Embed Search Engine
Thoughts on Standardizing Languages
Repeating Prompts
Trying New Things
Airbnb and Booking.com help Israelis make money from stolen Palestinian land
Re-ranking search results on the client side in Rust
Reranking search results on the client side in Rust
Re-ranking search results on the client side
Re:Google rejected me and now I'm building a search engine
on Tuesday July 02, 2024 @03:14PM (#40859608)
Yes, we veto sites to prevent spam.
I'm not sure you would like the results of what you suggest - if you are really going to crawl everything indiscriminately, you will end up with a lot of rubbish. Just check out Common Crawl if you want to get an idea of what it would look like.
Re:Google rejected me and now I'm building a search engine
on Tuesday July 02, 2024 @03:05PM (#40859545)
Yeah the ranking algorithm is just wrong right now. I'm working on it.
Re:Google rejected me and now I'm building a search engine
on Tuesday July 02, 2024 @03:03PM (#40859516)
The curated items will stay the same, but we can't expect all queries to be curated.
Re:Google rejected me and now I'm building a search engine
on Tuesday July 02, 2024 @02:48PM (#40859389)
I took the page down as it was attracting the wrong sort of attention. As some commenters surmised, the goal was to promote the search engine, but it wasn't working out that way...
Re:Google rejected me and now I'm building a search engine
on Tuesday July 02, 2024 @02:37PM (#40859300)
Spot on
Google rejected me and now I'm building a search engine
How do we know how good our search results are? [video]
The search engine where you choose the sites to crawl [video]
Show HN: Now tracking the number of unique URLs in the Mwmbl index
This is actually a lot harder to do than you might imagine, we need to scan the whole index and use a hyperloglog (handily implemented for us in Redis) to count the URLs.
Pentominoku for Layla
Pentominoku for Layla
Re:The Subscription Trap
on Saturday December 30, 2023 @12:46PM (#38817022)
Here's an alternative for streaming services that I've been trying out: buy second hand DVDs, rip them, then serve them with Plex. You can get 5 DVDs for £10 which is more than I can watch in a month, and less than I'd pay for Netflix, and the choice is huge, even if I restrict myself to these cheap ones.
Indexing a Billion Pages
NeurIPS 2023 Primer
Re:Ask HN: My partner gets rejected from jobs and we don't know why
on Thursday November 30, 2023 @04:50PM (#38479696)
I can't comment on the question as I'm not a designer and not in Germany, but there's a typo on the GitHub page: "tought" -> "thought".
Why is curation of web search results important?
Re:We are entering a new era of web search
on Wednesday November 29, 2023 @04:55PM (#38465865)
Hi HN! Would love to get your feedback on this idea and the feature. It is super early and there are lots of issues with it, but the basic idea is there.
We are entering a new era of web search
Mwmbl Update – Over 100M pages indexed
Re:Show HN: Unlock Your Productivity Potential
on Thursday November 02, 2023 @02:13PM (#38117760)
All I can see is a "continue with Google" button...