Ivan Kold

Learn how to build an image search app using a series of guided code commits with Developer Advocate Guy Royse. He’ll guide you through generating image embeddings using freely available Hugging Face models and storing them in Redis for fast, scalable semantic search.  The workshop covers: ▶️ What embeddings are and how they work ▶️ How to generate image embeddings and store them in Redis ▶️ Building a semantic search app with Redis, Python, and JavaScript Get access here: https://lnkd.in/gbZ3imbz

44

What Firms Actually Mean by “Strong C++” in 2026 𝗣𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗴𝗿𝗮𝗱𝗲 𝗖++  • Modern C++ (17/20+), RAII, ownership models  • Memory safety, cache locality, predictable allocation  • Writing systems that run 24/7 under load 𝗟𝗼𝘄-𝗹𝗮𝘁𝗲𝗻𝗰𝘆 𝗳𝘂𝗻𝗱𝗮𝗺𝗲𝗻𝘁𝗮𝗹𝘀  • Lock-free / wait-free design where it matters  • CPU pinning, NUMA awareness, branch prediction  • Understanding when optimization helps and when it doesn’t 𝗗𝗲𝗯𝘂𝗴𝗴𝗮𝗯𝗹𝗲 𝘀𝗽𝗲𝗲𝗱  • Deterministic behavior  • Reproducible performance issues  • Instrumentation and profiling built in, not bolted on 𝗪𝗵𝗲𝗿𝗲 𝗖++ 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝘀 𝗔𝗿𝗲 𝗕𝗲𝗶𝗻𝗴 𝗗𝗲𝗽𝗹𝗼𝘆𝗲𝗱  • Market data & feed handlers  • Execution & order routing  • Strategy infrastructure  • Core trading platforms 𝗪𝗵𝗮𝘁’𝘀 𝗖𝗵𝗮𝗻𝗴𝗲𝗱 𝗦𝗶𝗻𝗰𝗲 𝟮𝟬𝟮𝟯–𝟮𝟬𝟮𝟰  • Fewer “rewrite everything” projects  • More precise optimization of critical paths  • Tighter coupling between C++ engineers, quants, and FPGA teams  • Higher expectations per hire, smaller teams Connect & Follow to get more market insights! 

14

Learn about the trio powering Model Context Protocol (MCP)👇 🧠 Host = the LLM app (Claude Desktop, IDEs, even your Gradio Chatbots) 🧰 Server = the tool with specific capability (APIs or Gradio apps) 🔗 Client = maintains 1:1 connection with the Server from inside the Host Guides for further reading and building MCP-powered apps 👇 🚀 Create end-to-end applications with Gradio chat interface as the Host and Gradio apps as Servers: https://lnkd.in/gTpTJMCy 🔥 Create MCP Servers with Gradio for your IDEs, Claude Desktop, or custom Hosts: https://lnkd.in/g2yg-NGX

54

3 Comments

Yesterday, we shipped one of the first HyperEVM faucets. Today: archive nodes + WebSockets are live on Hyperliquid HyperEVM Mainnet 🚀 - Query past blocks with archive mode - Debug transactions with trace methods - Stream state with WebSockets All live now with Chainstack 👉 https://lnkd.in/d8KgFnvi

6

Autonomous agents can make decisions & take actions on their own to achieve goals, often using LLMs. In this article, Maham teaches you how to build an agentic system using Langbase's prompt chaining. You won't need any frameworks, & you'll learn about the Langbase SDK, Pipes, adding logic, and more. https://lnkd.in/gcgkW_rr

273

4 Comments

Here is Gemini CLI’s October 27th weekly update for v0.12.0 - 🎉 New Partner Extensions: - 🤗 Hugging Face extension: Access the Hugging Face hub. gemini extensions install https://lnkd.in/g2_Ek8Ua - Monday.com extension: Analyze your sprints, update your task boards, etc. gemini extensions install https://lnkd.in/gZbqPThi - Data Commons extension: Query public datasets or ground responses on data from Data Commons. gemini extensions install https://lnkd.in/g8dkRGsg - Model Selection: Choose the Gemini model for your session with /model. (abhipatel12) - Model Routing: Gemini CLI will now intelligently pick the best model for the task. Simple queries will be sent to Flash while complex analytical or creative tasks will still use the power of Pro. This ensures your quota will last for a longer period of time. You can always opt-out of this via /model. (abhipatel12) - Discussion: https://lnkd.in/gRPKHduA - Codebase Investigator Subagent: We now have a new built-in subagent that will explore your workspace and resolve relevant information to improve overall performance. (abhipatel12 and silviojr) - Enable, disable, or limit turns in /settings, plus advanced configs in settings.json (silviojr) - Explore Extension: Users can now open the extensions page in their default browser directly from the CLI using the /extensions explore command. (JayadityaGit) - Configurable Compression: Users can modify the compression threshold in /settings. The default has been made more proactive (scidomino). - API Key Authentication: Users can now securely enter and store their Gemini API key via a new dialog, eliminating the need for environment variables and repeated entry. (galz10) - Sequential Approval: Users can now approve multiple tool calls sequentially during execution. (joshualitt) https://lnkd.in/gcGSDux8 🧵 #GeminiCLI #Gemini #AI #OSS #HuggingFace #Monday

181

11 Comments

New in the Baseten ML Cookbook: a multi-node training recipe for MiniMax M2.5, the open MoE model that's SOTA in coding, agentic tool use, and search. The recipe runs Megatron-based SFT across 2 nodes of H200s with TP/EP parallelism, bf16 training, and configurable LoRA. One truss train push command to launch. https://lnkd.in/gGvK9Bqq

26

NEW: Smarter error messages for JSON healing ❤️‍🩹 LLMs break JSON more than you'd think. In December, we shipped the ability for OpenRouter to automatically fix malformed responses. Now with improved guidance returned for certain error cases: such as when models return arrays (68% of failures) or strings instead of objects. Docs: https://lnkd.in/g-5fQc86

25