TechnicalAI glossary
Prefix cache
Providers charge significantly less for a request prefix that has already been seen. If the same long preamble is sent with every call, always place it at the start and keep it identical: it will be cached. Moving it by even one character cancels the benefit.
In other words
The morning coffee always ordered the same: the waiter no longer needs to listen to the order.
Alyriaz articles that mention it
- Who decides that an incident is serious?
A company calls an incident "minor", the police "unacceptable". Who should decide how serious it is? A deeper question than it appears.
- Giving an identity to someone who does not exist?
Beijing grants papers to a virtual singer. Absurd? Our law already counts "persons" without bodies. What an identity really means.
- Free Gemini: what changes on October 9
From October 9, free Gemini only gets Flash-Lite, Google's smallest model. What changes, for whom, and whether it is worth paying.
- The week AI went "super"
Exodus at OpenAI, assistants that work non-stop, AI rebranded as "superintelligence": the week's key stories in five minutes.
- Claude Fable 5.1 and Mythos 5.1: agentic scores double and cache drops by 75%
Anthropic released Claude Fable 5.1 and Mythos 5.1 on 1 September, with a 75% drop in cache read pricing and sharply higher agentic scores. We analyse the release, the unusual structure of the two models, and what the distribution of gains reveals.
- What is "prompt caching"? The setting that could halve your AI bill
Prompt caching lets you avoid paying full price for the same context sent with every request. We explain the mechanism, the real savings, the pitfalls of cache lifetime, and why it's the first lever to pull before September's price hikes.