{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Machine Learning Tech Brief By HackerNoon","title":"Small Language Models, Not Giant LLMs, Should Power the Next Generation of AI Agents","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/81c6e999\"></iframe>","width":"100%","height":180,"duration":4086,"description":"\n        This story was originally published on HackerNoon at: https://hackernoon.com/small-language-models-not-giant-llms-should-power-the-next-generation-of-ai-agents.\nNVIDIA lays out why small language models, not giant LLMs, are the economical future of agentic AI, plus how to migrate agents to them.\nCheck more stories related to machine-learning at: https://hackernoon.com/c/machine-learning.\n            You can also check exclusive content about #nvidia-research, #small-language-models, #agentic-ai, #ai-agents, #slm-vs-llm, #llm-inference-cost, #edge-ai, #ai-agent-architecture,  and more.\nThis story was written by: @nvidiacorporation. Learn more about this writer by checking @nvidiacorporation's about page,\n            and for more stories, please visit hackernoon.com.\nNVIDIA researchers argue that most work done inside AI agents is narrow and repetitive, so small language models are capable enough, better suited, and far cheaper than giant general models. The paper lays out an algorithm for converting LLM-based agents to SLMs and addresses common objections.","thumbnail_url":"https://img.transistorcdn.com/KyA01h2FD2insgk-wX_xzV6vbJnTNl2BvPYVL-XaI9A/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9zaG93/LzQxMjcyLzE2ODM1/ODI0ODgtYXJ0d29y/ay5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}