Leapfrog, a small team doing high-volume AI visual and production work for fashion and brand clients, is building a "one brain" system that makes company knowledge and client context searchable through natural-language agents. The starter stack described is OpenClaw in a sandbox, a GitHub repository, Obsidian on the local machine, and Telegram as the access point. The system's research structure had roughly 1,200 files at the time of the talk.
NVIDIA Dynamo uses a unified session-level identifier to make its inference stack aware of agent sessions, subagents, and their KV cache across turns and tool calls. On SWE-bench, two TP4 MiniMax-M2 replicas on one 8xH100 node gained roughly 12-16% throughput from program-aware scheduling over KV-aware routing alone. The post also describes experimental shared-pool indexing and a proposed KvHint interface for session-aware cache policies in vLLM and SGLang.
AIWhy it matters: The post explains how session identifiers let an inference stack track agent working sets, with measured throughput gains on SWE-bench and agentic RL rollouts.
hi @bot look out for interesting things people are doing with Grok Bot on X and slack me a daily digest at 9am. if there’s anything relevant, pick the coolest ideas and suggest how I can use it to improve my workflow
Happening now: Join our webinar to discuss the future of search and retrieval, including Embed 5, Parse 5, and our new retrieval methodology, RCP-nDCG https://x.com/i/broadcasts/1DxLdZyjNXvxm
Databricks has put Workday Data Connect federation into Beta in Unity Catalog, letting teams query Workday HR and finance data without copying it. Workday Data Cloud customers get zero-copy, read-only access to the shared tables, with Databricks running queries and Unity Catalog governing access, lineage, and auditing. Teams can combine current people and financial data with other enterprise data for analytics and AI, including Genie-powered natural-language exploration.
SPACEXAI 🔥: Grok Bot can now search X! Earlier, Grok Bot would have to rely on web search or the X connector; with this release, it can match Grok's capabilities, where one prompt can trigger analysis of more than 100 X posts. I use Grok Bot on a daily basis to compose a Daily AI Brief - looks like it will get much better tomorrow. Testing time! 👀 https://x.com/bot/status/2107949161878606089/video/1
Perplexity is open-sourcing pplx-embed-v2-late, multi-vector embedding models for text and images in one shared space, in 9B and 0.6B sizes. The 9B model can index multimodal data, the 0.6B model can run queries on device, and PDF pages can be searched without OCR. The author reports 92.4% on MADQA and 64% on BrowseComp+, with weights available on Hugging Face.
On MADQA, 500 questions over 800 PDFs, it reaches 92.4%, the top result among retrievers.
In agentic search, a GPT-OSS-120B agent using the 9B model answers 64.0% of BrowseComp+ questions correctly, 4.9 points ahead of the next ColBERT model, with fewer searches than any baseline.
On Q2D-Web, about 70,000 production-derived search queries over 190M web documents, the 9B and 0.6B models reach 74.8% and 73.6% Recall@1000, against 69.3% for nemotron-embed-8b.
Both sizes are distilled token by token from one 18B teacher, so they share one embedding space. A corpus indexed with the 9B model can be searched with 0.6B queries. That lifts ViDoRe v3 from 62.3% to 63.5% with no added query cost.
The models also embed images and rendered pages directly, so PDFs, slides, and scans are searched without OCR, keeping tables, figures, and layout that text extraction drops.
Dense embedding models compress each document into one vector, which loses detail as pages get longer or more visual. pplx-embed-v2-late keeps a 128-dimensional vector per token and scores with MaxSim, so each query token is matched to its closest token in the document.
We're releasing pplx-embed-v2-late, two late-interaction embedding models that retrieve text, images, and pages with a shared embedding space for cross-model querying. Both models achieve frontier performance and are publicly available on Hugging Face. https://www.perplexity.ai/hub/blog/multimodal-embeddings-beyond-a-single-vector
The best search and retrieval platform is coming to the cloud. We want you to help test it. Compass Cloud is currently in private beta for those who want excellent retrieval with less overhead. If you're an enterprise team interested in early access, click below to apply ⬇️
Google DeepMind has released EmbeddingGemma 2, an open 740 million parameter model that maps text, images, audio, and video into one embedding space. It is built on the Gemma 4 architecture under an Apache 2.0 license and supports an 8K token context window. The company reports a code benchmark gain from 68.76 to 78.68 on MTEB Code and says the model can run on-device with about 567MB of active RAM for the full multimodal version on a Google Pixel 11 Pro.
AIWhy it matters: The release shows how a 740M-parameter embedding model can cover text, code, images, audio, and video on local hardware, with memory and storage figures to compare against other on-device options.
- Up to 14 reference images - Grounding with Google Search - Cleaner 1:4, 4:1, 1:8 and 8:1 panoramas at 2K and 4K - 1K $0.0336, 2K $0.0504, 4K $0.1134 per image https://openrouter.ai/google/gemini-nano-banana-2.1
4. 𝕏 sentiment tracker pick a topic and grok runs one x search per day for the last 10 days, drops the noise, and scores every post from -1 to +1. the dashboard shows the split, how sentiment moved day by day, and the posts behind the score. https://github.com/xai-org/xai-cookbook/tree/main/examples/x-sentiment-tracker
EmbeddingGemma 2 from @googlegemma, our compact 740M-parameter AI model built specifically for on-device and edge apps, has arrived. While the first-generation model delivered best-in-class text embedding, EmbeddingGemma 2 natively understands it all, connecting text, images, audio, and video in one shared space. This means you can search across different formats like text, images, audio, and video, without having to manually organize, translate, or label them first.
Google DeepMind released EmbeddingGemma 2, a 740M-parameter embedding model, under an Apache 2.0 license. The post says it is competitive across benchmarks and outperforms some specialist models more than twice its size, and that developers can use it for multimodal search or pair it with Gemma 4 for on-device RAG. Weights are available on Hugging Face and Kaggle.
Dell is adding agentic AI capabilities to its AI Data Platform, including a Unified Semantic Layer with a searchable glossary and an Enterprise Knowledge Graph built with Nvidia's Auto-Ontology open source library. The features are designed to give agents shared context, reducing repeated token generation and compute costs. The platform's layers include the Data Orchestration Engine, Data Engines, and Storage Engines such as PowerScale, ObjectScale, and the Lightning File System.
Google released EmbeddingGemma 2, an open embedding model under the Apache 2.0 license that maps text, code, images, video, and audio into a shared 768-dimensional space. Developers can load a 270M-parameter text and code setup, or add vision and audio encoders up to a 740M-parameter full multimodal model. Matryoshka truncation to 256 or 128 dimensions reduces vector storage, with the guide noting quality losses on image, video, and speech retrieval at lower dimensions.
AIWhy it matters: The guide gives concrete encoder sizes and dimension-storage tradeoffs, showing how to choose a configuration for text, code, image, video, and audio retrieval.
Google DeepMind launched EmbeddingGemma 2, an open-weight 740M parameter model that maps text, images, video frames, and audio into one vector space. The model can run on-device, with about 567MB active RAM for the full multimodal model on a Google Pixel 11 Pro, and is available through Google AI Edge Gallery, Google AI Edge Foresight on Mac, and MediaPipe Tasks, with ML Kit support coming in the weeks ahead.
AIWhy it matters: The post names concrete on-device apps, memory footprints, and latency figures, showing how a multimodal embedding model can power local search without cloud calls.
Databricks has made IP Functions generally available, letting users parse, validate, and join IPv4 and IPv6 addresses and CIDR blocks with built-in SQL functions optimized in Photon. In benchmarks versus another leading cloud data warehouse, CIDR joins ran up to 3.1x faster and cost up to 6.4x less. The functions support its Security Lakehouse vision for threat detection, investigation, and network analytics on one governed copy of data.
You can build custom vertical AI apps inside Computer, eg: guess spatial location of an image with 3D and satellite view.
Jev can search 🔍 through a long document just like you would! 🕵️
Cloudflare introduced a Web Search API through AI Gateway, partnering with Ceramic.ai, Exa, and Linkup to give agents fresh web results instead of guessed URLs. Requests appear in AI Gateway logs and draw from AI Gateway credits, with partners committing to Cloudflare's Verified bots crawling standards and including source links in results. Partners at list API pricing without markup are available via a REST endpoint or a Workers binding, with native server tools planned.
Ai2 released AstaBrief 8B, a model that turns a research question and retrieved literature excerpts into a cited report, along with its training data. In Asta's Generate a report feature, Fast mode averages 51.1 seconds per report versus 178.5 seconds for Thinking mode, about 3.5x faster. The model is built on Qwen3-8B with supervised fine-tuning and DPO, and institutions can run its open weights on their own infrastructure.
AIWhy it matters: The post explains the data filtering and one-pass generation choices behind a fast open-weights report model, showing what worked and what did not.
Jev is a phenomenal reranker, you heard that right.
New updates from us!
View pplx-embed-v2-context-9b-preview on Hugging Face: https://huggingface.co/perplexity-ai/pplx-embed-v2-context-9b-preview
On ConTEB, the preview has the highest average nDCG@10 of the models tested, though not on every task. It also beats voyage-context-4 on chunk retrieval while using 8x less storage per vector: 1 KB (1024 dims, int8) vs 8 KB (2048, float32).
pplx-embed-v2-context-9b-preview leads on Answer and Evidence retrieval at every cutoff. Document retrieval is closer, with our context v1 4B slightly ahead at Document@3 and Document@5.
context-bench is a benchmark for context-aware retrieval, created and privately held by @turbopuffer. Its queries, documents and capabilities are inspired by conversations with turbopuffer customers. It has 2,099 queries and 38,894 documents. We submitted for blind evaluation.
We overcome gold-chunk supervision limits by distilling relevance from our query-aware context compression model. It scores every document token against the query. Aggregated into chunk-level targets, those scores train the embedder to retrieve answer and supporting chunks.
Retrieval systems often split long documents into chunks, but this strips away the surrounding context. Contextual embedding models fix this by encoding the whole document once and pooling chunk vectors afterward. They are usually trained on one gold chunk per query.
We built a new way to train contextual embedding models, which encode each chunk of a document with the whole document in view. pplx-embed-v2-context-9b-preview sets a new state of the art on ConTEB and @turbopuffer's new, privately held context-bench. https://www.perplexity.ai/hub/blog/contextual-embedding-beyond-the-gold-passage
For the back of the room: • production-grade reranking for sales data with Jev • 20x faster • 10x cheaper • 12% more accurate Are you getting it yet?
Meta is testing Forum, a standalone iOS and Android app in the US that syncs with users' Facebook Groups to consolidate their conversations in one place. The update adds a new top-contributor role replacing previous badges, an AI-powered Ask feature that surfaces group posts and comments, and topic labels for exploring interests.
The United Nations system launched UN System Data Commons, an open-source platform built on Data Commons by Google that integrates siloed global statistics into one AI-ready knowledge graph. Users can query it in natural language, browse by location or theme, and use MCP-enabled AI agents to fetch verified figures and draft charts or reports. The UN plans to add more datasets, aiming to include 80% of UN system statistical datasets by 2027.