Small Language Models are the Future of Agentic AI · HackerPapers discussions

Small Language Models are the Future of Agentic AI — HN submission

Sat, 11 Oct 2025 15:29:17 GMT

Agentic web browsing can't scale with cloud LLMs

TLDR: - Agentic web browsing can’t scale if every page action triggers an LLM. - Small language models can power most interactive AI experiences. - The browser is the ideal runtime being open, GPU-accelerated, and everywhere. - Agentary.js is an open-source SDK for building agentic workflows that run locally, in the browser. Repo URL: https://github.com/agentary-ai/agentary-js --- Most agentic browsing today sends every click, scroll, or query to a cloud LLM. This doesn’t scale, economically or technically. Each DOM action becomes another API call that is slow and expensive, not to mention a…

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Small Language Models are the Future of Agentic AI — mentioned by selim-now

Wed, 01 Oct 2025 13:08:23 GMT

isn't that the premise of the Nvidia paper? https://arxiv.org/pdf/2506.02153

Paper and discussion history. A mention is not an endorsement.

Small Language Models are the Future of Agentic AI — HN submission

Thu, 18 Sep 2025 15:40:29 GMT

Launch HN: Cactus (YC S25) – AI inference on smartphones

Hey HN, Henry & Roman here, we are building Cactus (https://cactuscompute.com/), an AI inference engine specifically designed for phones. We're seeing a major push towards on-device AI, and for good reason: on-device AI decreases latency from >1sec to <100ms, guarantees privacy by default, works offline, and doesn't rack up a massive API bill at scale. Also, tools and agentic designs make small models really good beyond benchmarks. This has been corroborated by other papers like https://arxiv.org/abs/2506.02153, and we see model companies like DeepMind aggressively going into smaller models…

123 points; 63 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Small Language Models are the Future of Agentic AI — mentioned by mtone

Fri, 12 Sep 2025 15:51:55 GMT

Do you really need a H200 for this? Seems like something a consumer GPU could do. Smaller models might be ideal [0] as they don't require extensive world knowledge and are much more cost efficient/faster. Why can't you build this today? [0]: https://arxiv.org/pdf/2506.02153 Small Language Models are the Future of Agentic AI (Nvidia)

Paper and discussion history. A mention is not an endorsement.

Small Language Models are the Future of Agentic AI — mentioned by digitcatphd

Fri, 11 Jul 2025 18:09:39 GMT

https://arxiv.org/pdf/2506.02153

Paper and discussion history. A mention is not an endorsement.

Small Language Models are the Future of Agentic AI — HN submission

Tue, 01 Jul 2025 03:33:49 GMT

Small language models are the future of agentic AI

113 points; 45 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Small Language Models are the Future of Agentic AI — HN submission

Wed, 11 Jun 2025 11:16:33 GMT

Small Language Models Are the Future of Agentic AI

5 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.