2024-08-15
@simonw These non-standard, fine-grained pricing models are already starting to give off that awful AWS pricing vibe. This makes me somewhat reluctant to use the feature.
VentureBeat
Anthropic releases prompt caching, which lets developers cache frequently used context between API calls, in public beta on its API
Anthropic introduced prompt caching on its API, which remembers the context between API calls and allows developers to avoid repeating prompts.
2024-01-29
“But once you understand them, and you've got a feel for what they know, what they don't know, what they're good at, what kind of information you need to give them to get good results, you can absolutely fly with these things.” summarizes my experience w/ LLMs in the past 1.5y.
The Register
Q&A with Simon Willison, Django co-creator and an influential observer of AI software, on copyright concerns over AI, open-source AI models, LLMs, and more
Thomas Claburn / The Register : X: @j2bryson , @simonw , and @rednafi X: Joanna J Bryson / @j2bryson : @ylecun 1) the #AIAct will benefit ALL sized tech firms just as the GDPR did...