
AI developers, researchers, and professionals frequently hit a frustrating wall when analyzing large documents with LLMs: the hidden, compounding cost of context windows. Pasting a 200-page PDF into a chat isn’t a one-time charge. Because the conversation history is re-sent to the model on every single turn, that massive document is paid for again with every follow-up question. Marktechpost AI team just released Token Saver, an open-source Model Context Protocol (MCP) extension for Cla
Token Saver is an open-source extension that allows Claude to analyze PDF documents stored locally on a user's machine without uploading the files to external servers. The tool uses a hybrid retrieval system combining keyword matching and semantic search to extract only the relevant passages from a document, then sends those passages to Claude rather than the entire file. This approach reduces token consumption by 92 to 99 percent because users are charged only for the small relevant sections rather than the full document on every question. The extension matters because repeatedly asking questions about large PDFs normally requires re-sending the entire document with each follow-up query, creating significant costs, while Token Saver keeps documents private and limits what gets processed by the language model.

Long-running agents accumulate state that no transcript captures. A coding agent at step 10 holds edited files, a running dev server, installed packages, and a warm prompt cache. When it misreads a traceback and rewrites a file that was already correct, neither available recovery path is cheap: patching forward grows the context and the token bill, and restarting from step one re-pays every model and tool call while reproducing nothing exactly, because runs are non-deterministic. Jumping back t

New AI toolbars and prompts are showing up in Google Docs and Gmail. If you don’t want Gemini’s help in writing documents and emails, here’s how to turn that stuff off.

In October 2025, a storm brewed over the Caribbean Sea. Weather models differed on its trajectory. Would it remain weak and end up in Haiti, or would it intensify and head to Jamaica? Artificial intelligence model WeatherNext, developed by Google’s DeepMind and Google Research, went with the latter. Five days before landfall, it predicted with 80 percent confidence that the storm system would hit Jamaica as a Category 5 hurricane. Hurricane Melissa was catastrophic, causing flooding and landslid
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven