Hugging Face Blog
·
4 weeks ago
Research agents that combine private documents with web searches leak sensitive information through the cumulative pattern of their queries, even when individual searches appear innocuous. Across tested models, answer or full-information leakage reached 34.0% in baseline agents and climbed to 51.7% when agents were trained only for task performance. The Privacy-Aware Deep Research training method reduced leakage to 9.9% while maintaining 58.7% strict chain success by rewarding agents for constructing queries that avoid revealing private details.
Deep Learning Weekly
·
4 weeks ago
Deep Learning Weekly issue 460 covers multiple AI model releases and research advances, including Moonshot AI's Kimi K2.7 Code with 1T parameters achieving 31.5% benchmark improvements, Stanford's DeLM reducing multi-agent task costs by 50%, and Z.ai's GLM-5.2 with 753B parameters and 1M-token context window. Research papers include Data Journalist Agent for automated multimodal news generation and FastContext for specialized repository exploration in coding agents, which reduces token consumption by up to 60% while improving task resolution rates by 5.5%. The issue also features tools for LLM observability, cost optimization techniques for Claude Code, and infrastructure developments in multimodal model serving.
Ben's Bites
·
4 weeks ago
SpaceX is acquiring Cursor, an AI coding assistant, for $60 billion in stock. The acquisition price reflects the significant valuation of AI development tools in the current market. The deal marks a major consolidation in the AI tooling space, with Cursor's technology becoming part of SpaceX's broader operations.
Hugging Face Blog
·
4 weeks ago
Researchers benchmarked how well different language models can use the transformers library by measuring not just whether they got the right answer, but how much effort it took them to get there. The evaluation framework tested each task across three different tool access levels (bare install, cloned source code, or packaged skill) and found that adding a CLI reduced median task completion time but increased token consumption by 60% due to agents reading documentation. The results show that library design significantly affects agent efficiency—smaller models benefited more from curated documentation while larger models sometimes performed better with full source code access.
