FBI tries to unmask owner of archive.is

Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model

ICC ditches Microsoft 365 for openDesk

Open Source Implementation of Apple's Private Compute Cloud

I may have found a way to spot U.S. at-sea strikes before they're announced

Two billion email addresses were exposed

Mathematical exploration and discovery at scale

Eating stinging nettles

Hi everyone,For the past couple months I&#x27;ve been working on a website with two main features:- <a href="https:&#x2F;&#x2F;book.sv" rel="nofollow">https:&#x2F;&#x2F;book.sv</a> - put in a list of books and get recommendations on what to read next from a model trained on over a billion reviews- <a href="https:&#x2F;&#x2F;book.sv&#x2F;intersect" rel="nofollow">https:&#x2F;&#x2F;book.sv&#x2F;intersect</a> - put in a list of books and find the users on Goodreads who have read them all (if you don&#x27;t want to be included in these results, you can opt-out here: <a href="https:&#x2F;&#x2F;book.sv&#x2F;remove-my-data" rel="nofollow">https:&#x2F;&#x2F;book.sv&#x2F;remove-my-data</a>)Technical info available here: <a href="https:&#x2F;&#x2F;book.sv&#x2F;how-it-works" rel="nofollow">https:&#x2F;&#x2F;book.sv&#x2F;how-it-works</a>Note 1: If you only provide one or two books, the model doesn&#x27;t have a lot to work with and may include a handful of somewhat unrelated popular books in the results. If you want recommendations based on just one book, click the &quot;Similar&quot; button next to the book after adding it to the input book list on the recommendations page.Note 2: This is uncommon, but if you get an unexpected non-English titled book in the results, it is probably not a mistake and it very likely has an English edition. The &quot;canonical&quot; edition of a book I use for display is whatever one is the most popular, which is usually the English version, but this is not the case for all books, especially those by famous French or Russian authors.

Show HN: I scraped 3B Goodreads reviews to train a better recommendation model

Swift on FreeBSD Preview

I analyzed the lineups at the most popular nightclubs

You Should Write An Agent

I designed a relative piano-roll-based music notation. I used 12 colored arranged in a specific way to make visible the main effects and oppositions of Western tonal harmony. The tonic is always white, so a manual annotation&#x2F;interpretation is required for each MIDI file.All chords are flags of three to four colors. Minor mode is darker, major mode is lighter. Colors are arranged in thirds.I sorted the pieces from simple complex harmony. I also wrote a bit of text to explain what you may see. There&#x27;s also a corpus of structures: hyperlinks of tags that allow you to find similar patterns throughout my corpus of 3000+ popular pieces.My method makes chord progressions memorizable and instantly visible in the scores. No preparation of Roman numeral analysis &#x2F; chord symbols analysis is required. After a bit of training the chords will stare right in your eyes.It&#x27;s not synesthesia, it&#x27;s a missing script for tonal music which makes harmonically identical things look the same (or similar).I&#x27;ve also recorded lectures on my method in Russian (<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;playlist?list=PLzQrZe3EemP5pVPYMwBJGtiejiN3qtCce" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;playlist?list=PLzQrZe3EemP5pVPYMwBJG...</a>). I&#x27;m sorry I haven&#x27;t yet found time to re-record in English.I&#x27;ve also sketched a friendlier intro: <a href="https:&#x2F;&#x2F;vpavlenko.github.io&#x2F;d&#x2F;" rel="nofollow">https:&#x2F;&#x2F;vpavlenko.github.io&#x2F;d&#x2F;</a>Sorry, but this thing won&#x27;t make any sense if you&#x27;re color-blind.It&#x27;s open-source: <a href="https:&#x2F;&#x2F;github.com&#x2F;vpavlenko&#x2F;rawl" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;vpavlenko&#x2F;rawl</a>Earlier context: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=39165596">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=39165596</a>(Back then colors were less logical, and there was no corpus of 3000+ piece annotated yet)

Show HN: See chords as flags – Visual harmony of top composers on musescore

LLMs Encode How Difficult Problems Are

How often does Python allocate?

The Parallel Search API

Please stop asking me to provide feedback #8036

Universe's expansion 'is now slowing, not speeding up'

Springs and Bounces in Native CSS

I am excited to announce the release of TabPFN-2.5, our tabular foundation model that now scales to datasets of up to 50,000 samples and 2,000 features - a 5x increase from TabPFN v2, published in the Nature journal earlier this year. TabPFN-2.5 delivers state-of-the-art predictions in one forward pass without hyperparameter tuning across classification and regression tasks.What’s new in 2.5:
TabPFN-2.5 maintains the core approach of v2 - a pretrained transformer trained on more than hundred million synthetic datasets to perform in-context learning and output a predictive distribution for the test data. It natively supports missing values, cateogrical features, text and numerical features is robust to outliers and uninformative features.The major improvements:- 5x scale increase: Now handles 50,000 samples × 2,000 features (up from 10,000 × 500 in v2)- SOTA performance: TabPFN-2.5 outperforms tuned tree-based methods and matches the performance of a complex ensemble (AutoGluon 1.4), that itself includes TabPFN v2, tuned for 4 hours. Tuning the model improves performance, outperforming AutoGluon 1.4 for regression tasks.- Rebuilt API: New REST interface along with Python SDK with dedicated fit &amp; predict endpoints, making deployment and integration more developer-friendly- A distillation engine that converts TabPFN-2.5 into a compact MLP or tree ensemble while preserving accuracy and offer low latency inference.There are still some limitations. The model is designed for datasets up to 50K samples. It can handle larger datasets but that hasn’t been our focus with TabPFN-2.5. The distillation engine is not yet available through the API but only through licenses (though we do show the performance in the model report).We’re actively working on removing these limitations and intend to release newer models focused on context reasoning, causal inference, graph networks, larger data and time-series.
TabPFN-2.5 is available via API and a package on Hugging Face. Would love for you to try it and give us your feedback!Model report: <a href="https:&#x2F;&#x2F;priorlabs.ai&#x2F;technical-reports&#x2F;tabpfn-2-5-model-report" rel="nofollow">https:&#x2F;&#x2F;priorlabs.ai&#x2F;technical-reports&#x2F;tabpfn-2-5-model-repo...</a>Package: <a href="https:&#x2F;&#x2F;github.com&#x2F;PriorLabs&#x2F;TabPFN" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;PriorLabs&#x2F;TabPFN</a>Client: <a href="https:&#x2F;&#x2F;github.com&#x2F;PriorLabs&#x2F;tabpfn-client" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;PriorLabs&#x2F;tabpfn-client</a>Docs: <a href="https:&#x2F;&#x2F;docs.priorlabs.ai&#x2F;quickstart" rel="nofollow">https:&#x2F;&#x2F;docs.priorlabs.ai&#x2F;quickstart</a>

Show HN: TabPFN-2.5 – SOTA foundation model for tabular data