Is "GPU-hour per user" a sane way to price LLM inference?

Hacker News New2026-11-08 12:150 views

Points: 1

# Comments: 0

In Part 3 of this series , we built our Storage Vault in PostgreSQL 16: co-locating dense pgvector embeddings and full-t

💡 In one line: I built TrialSleuth AI , an agent that reviews a new drug before its first human trial and remembers ever

For weeks I have been measuring how far my own numbers can see, and the result was not flattering. On my own publishing

Quyết định chính thức giã từ sự nghiệp thi đấu quốc tế của Cristiano Ronaldo ở tuổi 41 đã chính thức khép lại kỷ nguyên

A quick roundup of developer news since the last digest. AI & tooling Secrets leaking through coding-agent permission pr

A company I worked with opened a new business line last spring. In the kickoff meeting one person talked for forty minut

Related posts