Ask HN: Do you subscribe to a hosted LLM or run local open-source models?
hanstyle · hn · 2026-10-09
An HN thread asks whether developers subscribe to hosted LLMs or deploy open-source models locally, and why. Respondents weigh privacy, cost, offline use, and capability — local small models for sensitive/high-volume work, subscriptions to Claude/ChatGPT for top-tier quality. Useful snapshot of real-world model selection habits among developers.
More from Infra
- IFM open-sources RL360: 8,192 concurrent sandboxes and ~1.3M rollouts for agentic RL — rupspace · 2026-10-23
- SpaceX seeks access to 80,000 US cell tower sites; Polymarket puts carrier odds at 29% — Polymarket · 2026-10-23
- Modular open-sources MAX framework to free AI compute from single-vendor lock-in — clattner_llvm · 2026-10-23
- Claude Models on Google Cloud (Anthropic managed) is now generally available — claudeai · 2026-10-23
- Scaling GLM-5.3-Flash training to 1M token context, 64x over Megatron baseline — AndrewLBeam · 2026-10-23
- Perplexity's Portable Computer lands on AMD Ryzen AI Max, running local 27B model — AravSrinivas · 2026-10-23