LLM & Text GenerationDev8 min reading time

LangChain State of AI 2023

LangChain
Read the full article
In 2023, LangChain analyzed anonymized data from its LangSmith platform to reveal how developers are building with large language models (LLMs). Retrieval methods dominate usage, with 42% of complex queries involving data retrieval, while 17% involve agent-based approaches. LangSmith supports both LangChain and non-LangChain users, aiding transition from prototype to production.

More in LLM & Text Generation

PyTorch Conference 2026: Google and Meta Open-Source TorchTPU for Native PyTorch on TPUs

InfoQ (AI, ML & Data)

Nanbeige Releases Nanbeige4.3-33B, a 33B Open Agentic Coding Model

MarkTechPost

Researchers from Stanford and UC Berkeley Introduce TokenGate: Token-Gated Attention Makes Long-Context Prefill Up to 11.3x Faster

MarkTechPost