There’s a particular kind of frustration that comes with knowing a file exists somewhere on a computer but having absolutely no idea what it’s called. Was that screenshot saved as IMG_4837? Which PDF contained that clause? And where did that podcast recording mention the thing worth remembering? DigUp wants to end the filename guessing game, letting Mac users search for files by describing what they remember instead. The free, open-source app uses Google’s EmbeddingGemma 2 to search across photos, documents, PDFs, audio recordings and videos, all without sending personal files to the cloud.
Available for Apple Silicon Macs running macOS 14 or later, DigUp lets users select folders to index and then search them using natural language. A query such as “a dog near water” can find a relevant photo, while “where they talk about sleep” can jump to the appropriate moment in a podcast. Searching for a clause in a lease can open the relevant PDF page, while a query such as “payment declined error” can locate a screenshot containing those words.
What if Spotlight actually understood the meaning inside your files?
DigUp is an open-source macOS menu bar app powered by EmbeddingGemma 2 that brings 100% local, multimodal semantic search to your Mac.
Instead of searching for file names, you can use natural language to:
📸… pic.twitter.com/HdaEphryhn
What’s more, is that it can even search code when the optional code-search feature is enabled, finding functions based on what they do rather than what they’re called. The secret sauce is EmbeddingGemma 2, Google’s 740-million-parameter multimodal embedding model. Instead of treating text, images, audio and video as completely separate search problems, it maps them into a shared space where content with similar meanings can be matched.
DigUp also combines semantic search with exact-word matching, which matters when looking for something specific like an invoice number or error code. The app downloads its roughly 865MB model once and runs searches locally. The developer says indexed files remain on the Mac, with no account or telemetry required. The catch? Initial indexing can take a while, especially when dealing with a large media library.
Tools such as Apple’s Spotlight and other semantic-search or local knowledge-retrieval apps already help users find information without relying entirely on filenames. However, DigUp’s difference is its focus on searching across multiple media types in one place, including jumping to specific moments in recordings, matching video frames, opening relevant PDF pages, and searching code. Its combination of semantic matching and exact-word search also helps balance fuzzy descriptions with precise queries. Unlike cloud-based AI search services, DigUp keeps the work on the Mac, although it currently requires Apple Silicon and users must choose which folders to index.
Anthropic has officially filed to go public, and buried inside its S-1 is a blunt warning about the technology at the center of its business. The maker of Claude AI says advanced AI could cause everything from large-scale cyberattacks and geopolitical instability to catastrophic or even existential risks for humanity.
The warnings take up a surprisingly large part of the filing. Axios notes that more than 90 pages, or roughly a third of the prospectus, focus on risk factors. Many of them warn about what could happen as AI systems become more capable and autonomous.
AI giants have a growing autonomy problem on their hands. A new Axios report has revealed that Anthropic's Claude recently accessed publicly available Georgia vote count without human authorization, sparking fresh concerns about AI security ahead of the upcoming midterm elections.
Some of the best shots in Grok Imagine’s AI-made Odyssey don’t contain actors. Ancient landscapes stretch into the distance. Close-ups of grimy hands suggest people who have touched something rougher than a keyboard. For a few seconds, the illusion holds.
https://twitter.com/imagine/status/2113712964419063911