@jeremyphoward

–

27 August 2024 18h50

…and also an AI regulation that removes jury trials and replaces them with LLMs as a judge — that's good too?

AI Regulation and LLM-Based Education: Ethical Concerns

By

–

27 August 2024 18h49

Cool. So you must be in favor then of an AI regulation that requires all children be taught entirely using LLM-created content at schools, since all AI regulations are good?

Cached Tokens Cost 25% More Storage

By

–

27 August 2024 18h47

Yes, cached tokens cost 25% more to store.

API Cache Storage Costs and TTL Configuration Explained

By

–

27 August 2024 18h39

Thanks for sharing! My first question was how much does it cost for cache storage and how does that work. I found the answer at the bottom of the api docs so hopefully this helps others with the same question. No extra storage costs and cache has a ~5 min TTL.

fa6-icons: Python library for Font Awesome icons

By

–

27 August 2024 18h03

I love the @fontawesome icon library, so I decided to make it easier to use from Python. Therefore, I've created a new fa6-icons library: https://
answerdotai.github.io/fa6-icons/ This works well with hypermedia applications, such as FastHTML, saving bandwidth by only including used icons.

Google Gemini API Caching: Explicit Payment Model Explained

By

–

27 August 2024 17h54

Google Gemini also supports caching, using an explicit API where you pay for the time your content is cached: https://
ai.google.dev/gemini-api/doc
s/caching?lang=python
…

Deepseek Introduces Fully Automated Prompt Caching Feature

By

–

27 August 2024 17h53

BTW Deepseek also provides prompt caching — and theirs is fully automated, which is pretty cool!

Anthropic Releases Official API Documentation on Prompt Caching Pricing

By

–

27 August 2024 17h52

Here's the official API docs with details on pricing: https://
docs.anthropic.com/en/docs/build-
with-claude/prompt-caching
…

Prompt Caching in Claude: Cost-Effective Token Optimization

By

–

27 August 2024 17h52

Something that nearly everyone is sleeping on is the importance of prompt caching. We've just added support for it to Claudette, so @AnthropicAI caching is now *very* easy to use — cached tokens are 90% cheaper, and faster! Docs here: https://
claudette.answer.ai/#prompt-caching