The Mathematics Search Engine

1+ min ago   (602+ words) Claude Haiku 5.5 is a candidate for the parts of an application that run often, need a quick response, and have a bounded definition of success. Anthropic positions it for classification, extraction, routing, summaries, compaction, and subagent work. That is a…...

13+ min ago   (241+ words) The first question is whether you can test it without sending information you cannot afford to disclose. If you cannot isolate public or owned non-sensitive examples, keep it out of the evaluation. If the test passes, decide whether behavior, output…...

8+ min ago   (796+ words) When you watch a video in HD, you probably don't think about how much data would have to be transmitted if there were no compression. The numbers would be staggering. Yet the video reaches you quickly and in good quality…...

6+ min ago   (996+ words) Evaluation is the companion to LLM observability: observability tells you a call was fast and cheap, evaluation tells you the answer was right. If you are running a model from my local LLM guide, you need both before you ship…...

6+ min ago   (1419+ words) What a local LLM actually is Why run a model on your own machine The fastest way in: Ollama in two commands The numbers I measured on a 16 GB M5 3B vs 7B: which one should you run Does the code it writes…...

6+ min ago   (1100+ words) LLM observability is the practice of recording what every model call actually does in production: how long it took, how many tokens it burned through, what that cost, plus whether it failed. The discipline grew out of the three pillars…...

10+ min ago   (146+ words) HCLTech has rolled out 20 purpose-built Industry AI Solutions targeting sector-specific business needs across banking, healthcare, aerospace, retail, telecom, mobility, energy and manufacturing. Several have already been deployed globally, while others are undergoing early-stage deployments. Hyderabad: HCLTech, a global technology company,…...

1+ week, 6+ day ago   (258+ words) One of the benefits of paid Medium membership is the ability to create new publications. Because most of my stories have not been published elsewhere, I have decided to create a new one, called Data And Beyond: This publication is…...

14+ min ago   (245+ words) So the best-suited models rise to the top. Thats what the latest OpenRouter data from Social Capital shows. In the last week of September, DeepSeek alone processed 36.8 trillion tokens on OpenRouter, more than OpenAI, Google, Anthropic and xAI combined (33 trillion)....

10+ min ago   (410+ words) A strategy can look great on historical data and still fail the moment conditions change. A beautiful backtest can be dangerous. A smooth equity curve. But there is one problem: The strategy has already seen the data. A backtest tells…...