Latest Tech News

Stay updated with the latest in technology, AI, cybersecurity, and more

Filtered by: embed Clear Filter

Show HN: Intercepting proxy for semantic search over visited pages

A proxy that embeds every web page you visit and lets you run similarity searches. Each successful HTTP GET 200 response (except for localhost) is re-fetched from pure.md to obtain clean Markdown. The cleaned text is embedded through llm. A minimal Flask UI provides search and cached-page views. Installation This is not a stand-alone program. It is a plugin for llm. If you are not using llm yet, install it with pipx first. pipx install llm Now you can install this plugin: llm install git+h

New embedding model leaderboard shakeup: Google takes #1 while Alibaba’s open source alternative closes gap

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now Google has officially moved its new, high-performance Gemini Embedding model to general availability, currently ranking number one overall on the highly regarded Massive Text Embedding Benchmark (MTEB). The model (gemini-embedding-001) is now a core part of the Gemini API and Vertex AI, enabling developers to build applications such as sema

All AI models might be the same

Project CETI is a large-scale effort to decode whale speech. If AI models do learn a universal language, we might be able to use it to talk to whales. Growing up, I sometimes played a game with my friends called “Mussolini or Bread.” It’s a guessing game, kind of like Twenty Questions. The funny name comes from the idea that, in the space of everything, ‘Mussolini’ and ‘bread’ are about as far away from each other as you can get. One round might go like this: Is it closer to Mussolini or bre

All AI Models Might be The Same

Project CETI is a large-scale effort to decode whale speech. If AI models do learn a universal language, we might be able to use it to talk to whales. Growing up, I sometimes played a game with my friends called “Mussolini or Bread.” It’s a guessing game, kind of like Twenty Questions. The funny name comes from the idea that, in the space of everything, ‘Mussolini’ and ‘bread’ are about as far away from each other as you can get. One round might go like this: Is it closer to Mussolini or bre

Lua beats MicroPython for serious embedded devs

Why Lua Beats MicroPython for Serious Embedded Devs In professional embedded projects, ranging from industrial automation to medical devices and commercial IoT products, developers increasingly favor high-level, lightweight, and easy-to-use environments. While MicroPython has earned praise for rapid prototyping and field deployments on microcontrollers, its active ecosystem is largely centered around hobbyist boards. It is important to note that Python’s greatest strength, its vast library eco

LGND wants to make ChatGPT for the Earth

The Earth is awash in data about itself. Every day, satellites capture around 100 terabytes of imagery. But making sense of it isn’t always easy. Seemingly simple questions can be fiendishly complex to answer. Take this question that is of vital economic importance to California: How many fire breaks does the state have that might stop a wildfire in its tracks, and how have they changed since the last fire season? “Originally, you’d have a person look at pictures. And that only scales so far,”

Muvera: Making multi-vector retrieval as fast as single-vector search

Neural embedding models have become a cornerstone of modern information retrieval (IR). Given a query from a user (e.g., “How tall is Mt Everest?”), the goal of IR is to find information relevant to the query from a very large collection of data (e.g., the billions of documents, images, or videos on the Web). Embedding models transform each datapoint into a single-vector “embedding”, such that semantically similar datapoints are transformed into mathematically similar vectors. The embeddings are

AllTracker: Efficient Dense Point Tracking at High Resolution

Sorry, your browser doesn't support embedded videos. Overview We introduce AllTracker: a model that estimates long-range point tracks by way of estimating the flow field between a query frame and every other frame of a video. Unlike existing point tracking methods, our approach delivers high-resolution and dense (all-pixel) correspondence fields, which can be visualized as flow maps. Unlike existing optical flow methods, our approach corresponds one frame to hundreds of subsequent frames, rath