I’m More Interested in Why Things Break Than Why They Work I don’t think I became interested in technology because I wanted to build apps. I think I became interested because I wanted to understand things. There’s a difference. When something works exactly as expected, there usually isn’t much mystery left. You press a button, something happens, and you move on.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.
Article URL: https://openai.com/index/sharing-ai-progress-in-mathematics/ Comments URL: https://news.ycombinator.com/item?id=49984923 Points: 24 # Comments: 4
A wise man once said, “if the young man is hungry, he should go to the forest and hunt the elephant. If he kills the elephant, the hunger ends, and if the elephant kills him, the hunger ends.” My Monday poverty motivation led me to brave the waters of quantitative trading using algorithmic bots. As a Nigerian, familiar with unsteady power supply, I asked early: “how can I achieve 100% runtime even if I don’t get light for a week?” The answer led me to a VPS (Virtual Private Server). Ladies and gentlemen, tell me why the cheapest monthly subscription for a Windows OS is $50. My entire trading e
“Download a new JavaScript bundle and run it” describes transport. It does not describe a production release system. A real React Native OTA implementation has to preserve compatibility with installed binaries, identify immutable artifacts, decide which release each device should receive, verify downloads, control activation, observe adoption, and recover when an update fails. Those are separate boundaries. Treating them as one download call is how a convenient feature becomes an operational risk.
Send FP32, get 2x to 32x compression, and leave your ingestion pipeline untouched. The engine does the work. The previous article in this series put the quantization work on you. You convert vectors to a reduced precision before indexing, and Amazon OpenSearch Service stores exactly what you send. That gives you full control, and it gives you a standing job: pick a method, run the conversion in your pipeline, and re-check accuracy every time your embedding model changes.
Discussion (0)
Log in to join the discussion and vote.
Log in