Launch HN: Nucleus (YC S22) – Kubernetes platform for both devs and ops

69 points by evisdrenova 3 years ago | 36 comments

Ask HN: How can ChatGPT serve 700M users when I can't run one GPT-4 locally?

474 points by superasn 1 year ago | 304 comments

Ask HN thread asking how OpenAI serves ChatGPT to 700M weekly users when a GPT-4-class model is hard to run locally, seeking inference scaling insights.

Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents

151 points by vishnukool 14 days ago | 104 comments

Launch HN post for Agent37, a YC startup offering low-cost sandboxes for running AI agents, explaining its cost-reduction techniques like gVisor and non-hyperscaler hosts.

Launch HN: Outerport (YC S24) – Instant hot-swapping for AI model weights

89 points by tovacinni 2 years ago | 20 comments

Launch HN: Cerebrium (YC W22) – Serverless Infrastructure Platform for ML/AI

46 points by za_mike157 2 years ago | 32 comments

Launch HN: Consus (YC F24) – LLM gateway for companies handling sensitive data

32 points by ericmags 13 days ago | 16 comments

Launch HN post for Consus, a YC F24 LLM gateway routing AI requests to ITAR- and CUI-compliant government cloud infrastructure for aerospace and defense companies.