Ad
Short

Anthropic's prompt caching feature can cut the cost of long prompts by up to 90% and reduce latency by as much as 85%. The technology lets developers cache frequently used context between API calls, giving Claude more background knowledge and examples to work with. Prompt caching is now in public beta for Claude 3.5 Sonnet and Claude 3 Haiku models, with support for Claude 3 Opus on the way. The feature is a good fit for chat agents, coding assistants, long document processing, detailed instruction sets, agent-based search and tool usage. It also works well for answering questions about books, papers, documentation, and podcast transcripts, Anthropic says. Google also offers prompt caching.

Ad
Ad
Ad
Ad
Ad
Ad
Short

Anthropic is expanding its bug bounty program to test its "next-generation system for AI safety mitigations." The program focuses on identifying and defending against "universal jailbreak attacks." Anthropic is prioritizing critical vulnerabilities in high-risk areas like chemical, biological, radiological and nuclear (CBRN) defense and cybersafety. Participants get early access to Anthropic's latest safety systems before public release. Their task is to find vulnerabilities or ways to bypass safety measures. Anthropic is offering rewards up to $15,000 for discovering new universal jailbreak attacks.

Google News