Bing's web grounding already powers almost every major AI chatbot today. With Harrier, it just got a big upgrade for the agentic era. Better embeddings lead to better retrieval, often more accurate answers, and better multilingual performance in the 100+ languages Harrier
AGENTS
-
Bing releases Harrier, new state-of-the-art embedding model
By
–
Another SOTA model drop! This time from the @Bing team: meet Harrier, a new open-source embedding model with state-of-the-art performance and the #1 spot on the industry standard multilingual MTEB-v2 benchmark. Jordi Ribas (@JordiRib1) I’m pleased to share that our search team has open sourced an embedding model called Harrier that is currently ranking #1 on the multilingual MTEB-v2 benchmark leaderboard. Harrier delivers SOTA performance on retrieval quality, semantic matching, and contextual analysis across workloads, supporting more than 100 languages and handles long inputs up to 32K. It is built for the next generation semantic search for Bing and our web grounding (RAG) service for AI agents, which already powers nearly every major AI chatbot today. As you can see in the leadership board, our Harrier model is currently ahead of other excellent models based on Gemini, Gemma, Llama, Qwen, and more. I’m grateful for the hard work of our team to get to this top ranking, and I’m excited to see all the healthy competition in the space, which should ultimately lead to more innovations that will benefit everyone. Learn more: msft.it/6019QNB0b — https://nitter.net/JordiRib1/status/2041550352739164404#m
→ View original post on X — @clementdelangue, 2026-04-07 16:22 UTC
-
GLM-5.1: Open Source AI Model Achieves Top Performance Rankings
By
–
Introducing GLM-5.1: The Next Level of Open Source – Top-Tier Performance: #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo. – Built for Long-Horizon Tasks: Runs autonomously for 8 hours, refining strategies through thousands of iterations. Blog: z.ai/blog/glm-5.1 Weights: huggingface.co/zai-org/GLM-5… API: docs.z.ai/guides/llm/glm-5.1 Coding Plan: z.ai/subscribe Coming to chat.z.ai in the next few days.
→ View original post on X — @scobleizer, 2026-04-07 16:14 UTC
-
Superset: New IDE for Parallel AI Agent Execution
By
–
introducing superset
— Superset (@superset_sh) 7 avril 2026
the IDE for the AI agent era
stop waiting on coding agents
run them in parallel pic.twitter.com/wJcHmynG35introducing superset the IDE for the AI agent era stop waiting on coding agents run them in parallel
→ View original post on X — @scobleizer, 2026-04-07 16:10 UTC
-
Clément finds Mario’s agentic prompts amusingly harsh and direct
By
–
It's so fun to read @badlogicgames agentic prompts, maybe I'm too kind with my agents 🙂 "jesus fuck, i'm so fucking confused wtf are you doing?"
→ View original post on X — @clementdelangue, 2026-04-07 16:09 UTC
-
AI Expert Curates Comprehensive AI Lists on X Platform
By
–
I put you in my AI lists which are the most complete on X: https://
x.com/scobleizer/lis
ts
… -
Launch Your Product with Replit Agent 4 Buildathon
By
–
Launch your Product with Replit – Agent 4 Buildathon https://
x.com/i/broadcasts/1
RKZzjDZYOMKB
… -
LangSmith: Debugging and Optimizing AI Agents in Production
By
–
LangSmith 🤝Fix your agents
— Harrison Chase (@hwchase17) 7 avril 2026
You'll see our billboards around SF and NYC over the next few months.
The themes all point to the same problem: you don't know what your agents will do until you actually run them. What works in demos can break in the real world. Without tracing and… pic.twitter.com/IRKrj7J1y7LangSmith 🤝Fix your agents You'll see our billboards around SF and NYC over the next few months. The themes all point to the same problem: you don't know what your agents will do until you actually run them. What works in demos can break in the real world. Without tracing and evals, you're just guessing at why. Track what your agent actually does. Optimize and fix your agents. Then measure whether your fixes work. That loop is how agents get better, and LangSmith is built to power that workflow. If you spot one around, send it our way!
-
Composio: Secure AI Agents Without Exposing API Keys
By
–
Every dev building AI agents has pasted API keys into a .env and said “I’ll fix it later.”@steipete this is exactly what Composio fixes.
— AI Highlight (@AIHighlight) 7 avril 2026
No keys in the agent’s context. It just acts without ever knowing what powered it. https://t.co/no9FN0ygO8Every dev building AI agents has pasted API keys into a .env and said “I’ll fix it later.” @steipete this is exactly what Composio fixes. No keys in the agent’s context. It just acts without ever knowing what powered it. Karan Vaidya (@KaranVaidya6) Your AI agent is in bed with you. No protection. You just wanted it to work. Gmail. Allow. Calendar. Allow. Slack, Notion, GitHub. Allow. Allow. Allow. Every password, handed over. Your agent never needed a single one. They just needed @Composio Secure your agents in minutes ↓ composio.dev/protection — https://nitter.net/KaranVaidya6/status/2041516353551737338#m
→ View original post on X — @aihighlight, 2026-04-07 15:54 UTC
-
Powerful Agents Need Secure OAuth Architecture Shifts
By
–
People keep building powerful agents and leaving the front door wide open. The OAuth happens on Composio's infrastructure, the agent gets a reference, never the key. That's the architecture shift no one is talking about.