Abstract We introduce MusicLM, a model generating high-fidelity music from text descriptions such as "a calming violin melody backed by a distorted guitar riff". MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and it generates music at 24 kHz that remains consistent over several minutes. Our experiments show that MusicLM outperforms previous systems both in audio quality and adherence to the text description. Moreover, we demonstrate that MusicLM can be conditioned on both text and a melody in that it can transform whistled and hummed melodies according to the style described in a text caption. To support future research, we publicly release MusicCaps, a dataset composed of 5.5k music-text pairs, with rich text descriptions provided by human experts.

Once a commit cements itself in git’s history—that’s it. It’s impossible to amend a commit message buried deep in a repo’s log.

But git notes enable you to amend new information about old commits in a special namespace. And they’re capable of so much more.

Notes stow metadata about anything tracked by git—any object: commits, blobs, and trees. All without futzing with the object itself.

A tree view (collapsible list) can be created using only HTML and CSS, without the need for JavaScript. Accessibility software will see the tree view as lists nested inside disclosure widgets, and the standard keyboard interaction is supported automatically.

I spent some months following BTS and Blackpink and others, butchering my algorithmic recommendations in the process, and concluded that there are four key things all K-pop bands do to cultivate their fandoms. I’ll describe each below, along with examples of how founders and execs can modify these tactics to build passion for a product, brand, or mission. No dancing required.

In this post I will show you how to break down Linux system load by the load contributor or reason. You can drill down into the “linux system load in thousands” and “high system load, but low CPU utilization” problem patterns too.

With this demo, you can supply an Input string and see the combinations that are confusable with it, using data collected by the Unicode consortium. You can also try different restrictions, using characters valid in different approaches to international domain names.

TL;DR: OSC52 is an ANSI escape sequence that allows you to copy text into your system clipboard from anywhere, including from remote SSH sessions. Check vim-oscyank, a plugin which integrates OSC52 into Vim.

The world’s most widely used web app scanner. Free and open source. Actively maintained by a dedicated international team of volunteers.

In its simplest form, git worktree add <path> automatically creates a new branch whose name is the final component of <path>, which is convenient if you plan to work on a new topic. For instance, git worktree add ../hotfix creates new branch hotfix and checks it out at path ../hotfix. To instead work on an existing branch in a new worktree, use git worktree add <path> <branch>. On the other hand, if you just plan to make some experimental changes or do testing without disturbing existing development, it is often convenient to create a throwaway worktree not associated with any branch. For instance, git worktree add -d <path> creates a new worktree with a detached HEAD at the same commit as the current branch.

If a working tree is deleted without using git worktree remove, then its associated administrative files, which reside in the repository (see "DETAILS" below), will eventually be removed automatically (see gc.worktreePruneExpire in git-config[1]), or you can run git worktree prune in the main or any linked worktree to clean up any stale administrative files.

The basic insight behind Levenshtein automata is that it's possible to construct a Finite state automaton that recognizes exactly the set of strings within a given Levenshtein distance of a target word. We can then feed in any word, and the automaton will accept or reject it based on whether the Levenshtein distance to the target word is at most the distance specified when we constructed the automaton. Further, due to the nature of FSAs, it will do so in O(n) time with the length of the string being tested. Compare this to the standard Dynamic Programming Levenshtein algorithm, which takes O(mn) time, where m and n are the lengths of the two input words! It's thus immediately apparrent that Levenshtein automaton provide, at a minimum, a faster way for us to check many words against a single target word and maximum distance - not a bad improvement to start with!

Of course, if that were the only benefit of Levenshtein automata, this would be a short article. There's much more to come, but first let's see what a Levenshtein automaton looks like, and how we can build one.