LangChain Blog
-
1
How we build evals for Deep Agents
-
2
How Kensho built a multi-agent framework with LangGraph to solve trusted financial data retrieval
-
3
Agent Evaluation Readiness Checklist
-
4
Announcing the LangChain + MongoDB Partnership: The AI Agent Stack That Runs On The Database You Already Trust
-
5
March 2026: LangChain Newsletter
-
6
Open Models have crossed a threshold
-
7
How My Agents Self-Heal in Production
-
8
Continual learning for AI agents
-
9
Arcade.dev tools now in LangSmith Fleet
-
10
Deep Agents v0.5
AI-Tech Park
-
1
Databricks, Microsoft Expand Partnership to Advance Enterprise AI
-
2
Cognyte Appoints Adam Philpott as CRO to Lead Global Market Expansion
-
3
MulticoreWare, AMD Partner to Advance Physical AI and Robotics
-
4
Ardent Partners, Ivalua Study Reveals AI Procurement Execution Gap
-
5
Lorikeet Appoints Jerry Brooner Chief Revenue Officer
-
6
mimik Operationalizes Agentic AI on AMD Ryzen AI Embedded X100
-
7
Kong Opens Paris, Milan Offices Amid EMEA Growth
-
8
StrongestLayer Raises $9.3M Total Seed to Combat AI Email Attacks
-
9
Infinium Edge Announced the Launch of EdgeSites™
-
10
Alibaba’s Amap Launches Full-Stack ABot Upgrade for Embodied AI Robots
Interconnects
-
1
Was I wrong about open models & cyber risks?
-
2
Artificial Analysis v5 and the benchmarker's dilemma
-
3
Podcast: Kimi K3.1 Pro, the new cyber reality, and Muse musings
-
4
Latest open artifacts (#25): DeepSeek V4.1 Flash 1017, American-made models, and new regulatory controls in the US & China
-
5
Meta shakes up the frontiers, open and closed
-
6
I expect rapid progress but not towards general superintelligence
-
7
The Cyber Risk Discourse is Broken
-
8
Debating RSI, the US-China Gap, and Jaggedness with JS Denain of Epoch AI
-
9
The current balance of power in open models
-
10
Why I still haven’t bought into true RSI
MarkTechPost
-
1
Edge0 Releases Audio8-TTS-Realistic, a 0.6B Voice Cloning TTS Model
-
2
Samaya AI Releases Sterling: A 3B-Active Finance Research Agent Model that Beats Claude Fable 5.1 on FrontierFinance at 11x Lower Cost
-
3
AI Security Agents Compared: Claude, Codex, Mantis, Cloudflare
-
4
Meet TokenEconomizer: Microsoft’s Plugin That Cuts Coding Agent Costs by Up to 30.9%
-
5
Vercel Labs Open-Sources agent-desktop for Agent Computer Use
-
6
NVIDIA Releases Nemotron 3.5 Transcribe: An Open 30B MoE Model for 40-Language Transcription with ~4B Active Parameters
-
7
AssemblyAI Ships AssemblyAI-TTS-1: A $15 per 1M Character Text-to-Speech API for Voice Agents
-
8
Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech
-
9
Infini-AI-Lab Releases Hermit, an Open-Source Harness Adapter Framework for AI Agents
-
10
Prime Intellect Releases Prime Mega MoE: Trainable Fused MoE Kernel, 3.11x Faster Forward Pass
Towards AI – Medium
-
1
Can AI Browsers Ever Be Made Safe From Prompt Injection?
-
2
How Claude Code Works (Let’s Build a Tiny One)
-
3
Microsoft Fabric Workloads: Which One Should Your Team Use?
-
4
Part XIX — Spark on Kubernetes: Executor Sizing and Dynamic Allocation
-
5
[Day 36/100] Mem0 in Practice: Long-Term Memory That Decides What Your Agent Forgets
-
6
Tracing AI Agents: What OTel’s GenAI Spans Actually Capture
-
7
A School Form Took Me 30 Minutes. “Just Use AI” Missed 4 in 10 Blanks.
-
8
[Day 37/100] Build Your Own Agent Memory Layer with Postgres and pgvector
-
9
My Model Thought Tamil Was Telugu: Open-Source Language ID for Hinglish, Tanglish and Kanglish
-
10
The Worst Ways to Use AI Are the Ones That Feel Productive
Ahead of AI
-
1
Build Your Own Reasoning Model: A Full Video Course
-
2
Language Models for Text Classification: From Bag-of-Words to Jev
-
3
GPT-6 Astra, Looped Transformers, and Hidden Reasoning
-
4
How Claude Watermarks AI-Generated Text
-
5
Building an AI Text Detector From Scratch
-
6
Controlling Reasoning Effort in LLMs
-
7
The State of Reinforcement Learning for LLM Reasoning
-
8
Coding LLMs from the Ground Up: A Complete Course
-
9
Understanding and Coding the KV Cache in LLMs from Scratch
-
10
LLM Research Papers: The 2025 List (January to June)
Weights & Biases: Fully Connected
-
1
Machine learning for fraud detection in banking
-
2
Dense vs. Paper-Inspired Sparse Transformers: A Three-Hour OpenWebText Benchmark
-
3
Tutorial: Jev-as-a-Judge for LLM Evals
-
4
Comparing Modern Transformer Architectures at GPT-2 Scale with ARIA and W&B
-
5
Tutorial: Running inference with Kimi K2.7 Code using CoreWeave Inference (Serverless)
-
6
Getting started with Kimi 2.7 on CoreWeave Inference (Serverless)
-
7
Agent Evaluation Benchmarks: A Practitioner's Guide to Choosing the Right Test
-
8
Understanding the Muon Optimizer : Explained and Tested against AdamW with NanoGPT
-
9
Retrieval augmented generation (RAG) in production
-
10
Understanding HRM-Text-1B - A tutorial