New KV cache compaction technique cuts LLM memory 50x without accuracy loss

MIT researchers developed Attention Matching, a KV cache compaction technique that compresses LLM memory by 50x in seconds — ...
The Next Web

Google made Gmail and Drive easier for AI agents to use

Google’s new Workspace CLI unifies Gmail, Drive, and Calendar for AI agents, with OpenClaw support and MCP integration built in from day one.
NPR

Code Switch

What's CODE SWITCH? It's the fearless conversations about race that you've been waiting for. Hosted by journalists of color, our podcast tackles the subject of race with empathy and humor. We explore ...