Tag

#llm

26 articles

Reading Zhipu’s GLM-5.3 results past the headline number

Learn how to analyze LLM benchmark results beyond headline numbers by examining improvement patterns across different domains, using real-world data analysis techniques.

Aug 1835

Top LLM Observability and Evaluation Platforms in 2026: Langfuse, LangSmith, Braintrust, Arize, and More Compared

Learn how to integrate LangSmith for LLM observability and evaluation, including tracing, performance monitoring, and output evaluation.

Aug 920

Cursor Releases Cursor Router: A Request-Level Classifier Delivering Frontier Coding Quality at 30–50% Lower Cost

This article explains Cursor Router, an AI system that intelligently routes requests to the most suitable language model, achieving 30-50% cost savings while maintaining high-quality outputs.

Jul 2230

tech

Moonshot pauses new Kimi K3 subscriptions after GPU demand maxes out in 48 hours

Learn to build a GPU resource management system that monitors utilization and dynamically controls LLM subscriptions, similar to what Moonshot implemented for Kimi K3.

Jul 1957

Google Cloud’s Always-On Memory Agent Replaces RAG and Embeddings With Continuous LLM Consolidation on Gemini 3.1 Flash-Lite

Learn to build a simplified Always-On Memory Agent using Gemini 3.1 Flash-Lite that treats memory as a continuous process without vector databases.

Jul 1769

Tencent Releases Hy3: An Open 295B Mixture-of-Experts (MoE) Model with 21B Active Parameters and 256K Context

Learn how to access and use Tencent's Hy3 Mixture-of-Experts model through OpenRouter, including understanding MoE architecture, using long-context capabilities, and experimenting with reasoning tasks.

Jul 6100

The 7 Types of Agent Memory: A Technical Guide for AI Engineers

Explore the seven types of agent memory that enable AI systems to maintain context, learn from experience, and perform complex, long-term tasks.

Jun 2186

VibeThinker-3B: A 3B Dense Reasoning Model Built on Qwen2.5-Coder-3B With the Spectrum-to-Signal Post-Training Pipeline

Learn how to load, test, and evaluate the VibeThinker-3B reasoning model using Hugging Face transformers and Python.

Jun 1980

Salesforce CodeGen Tutorial: Generate, Validate, and Rerank Python Functions With Unit Tests and Safety Checks

An advanced tutorial on Salesforce CodeGen demonstrates how to generate, validate, and refine Python functions using large language models, incorporating syntax checking, unit tests, and safety measures.

Jun 1857

Google Research Adds Agentic RAG to Gemini Enterprise Agent Platform with a Sufficient Context Agent for multi-hop queries

Learn to build a simplified version of Google's agentic RAG framework with Sufficient Context Agent for handling multi-hop queries and improving factuality accuracy.

Jun 771

NVIDIA AI Releases Nemotron 3 Ultra: An Open 550B Mixture-of-Experts Hybrid Mamba-Transformer for Long-Running Agents

Learn to set up and run inference with NVIDIA's Nemotron 3 Ultra, a 550B parameter hybrid Mamba-Transformer model designed for long-running AI agents with extended context windows.

Jun 490

Best Enterprise Level Agentic AI Platforms for 2026

This explainer explores agentic AI—intelligent systems that perceive, reason, and act autonomously in enterprise environments. Learn how these platforms are transforming business operations through automation and cross-system orchestration.

May 1871