Prompt-caching – auto-injects Anthropic cache breakpoints (90% token savings)

Related Stories

• AWS plans to deploy Cerebras' Wafer-Scale Engine chip for AI inference functions; AWS will still offer slower, cheaper computing using its Trainium processors
• Will AI Save Consumers From Smartphone-Based Phishing Attacks?
• AI is exhausting workers so much, researchers have dubbed the condition ‘AI brain fry’
• Peacock is adding an AI Andy Cohen to narrate an endless stream of Bravo clips
• Peacock expands into AI-driven video, mobile-first live sports, and gaming