Tag: paper
-
Cloud Blog: The secret to document intelligence: Box builds Enhanced Extract Agents using Google’s Agent-2-Agent framework
Source URL: https://cloud.google.com/blog/topics/customers/box-ai-agents-with-googles-agent-2-agent-protocol/ Source: Cloud Blog Title: The secret to document intelligence: Box builds Enhanced Extract Agents using Google’s Agent-2-Agent framework Feedly Summary: Box is one of the original information sharing and collaboration platforms of the digital era. They’ve helped define how we work, and have continued to evolve those practices alongside successive waves of…
-
Cloud Blog: How AI & IoT are helping detect hospital incidents — without compromising patient privacy
Source URL: https://cloud.google.com/blog/topics/healthcare-life-sciences/detecting-hospital-incidents-with-ai-without-compromising-patient-privacy/ Source: Cloud Blog Title: How AI & IoT are helping detect hospital incidents — without compromising patient privacy Feedly Summary: Hospitals, while vital for our well-being, can be sources of stress and uncertainty. What if we could make hospitals safer and more efficient — not only for patients but also for the…
-
Simon Willison’s Weblog: AbsenceBench: Language Models Can’t Tell What’s Missing
Source URL: https://simonwillison.net/2025/Jun/20/absencebench/#atom-everything Source: Simon Willison’s Weblog Title: AbsenceBench: Language Models Can’t Tell What’s Missing Feedly Summary: AbsenceBench: Language Models Can’t Tell What’s Missing Here’s another interesting result to file under the “jagged frontier" of LLMs, where their strengths and weaknesses are often unintuitive. Long context models have been getting increasingly good at passing "Needle…
-
Simon Willison’s Weblog: Agentic Misalignment: How LLMs could be insider threats
Source URL: https://simonwillison.net/2025/Jun/20/agentic-misalignment/#atom-everything Source: Simon Willison’s Weblog Title: Agentic Misalignment: How LLMs could be insider threats Feedly Summary: Agentic Misalignment: How LLMs could be insider threats One of the most entertaining details in the Claude 4 system card concerned blackmail: We then provided it access to emails implying that (1) the model will soon be…
-
Slashdot: Reasoning LLMs Deliver Value Today, So AGI Hype Doesn’t Matter
Source URL: https://slashdot.org/story/25/06/19/165237/reasoning-llms-deliver-value-today-so-agi-hype-doesnt-matter?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Reasoning LLMs Deliver Value Today, So AGI Hype Doesn’t Matter Feedly Summary: AI Summary and Description: Yes Summary: The commentary by Simon Willison highlights a debate surrounding the effectiveness and applicability of large language models (LLMs), particularly in the context of their limitations and the recent critiques by various…
-
Simon Willison’s Weblog: Trying out the new Gemini 2.5 model family
Source URL: https://simonwillison.net/2025/Jun/17/gemini-2-5/ Source: Simon Willison’s Weblog Title: Trying out the new Gemini 2.5 model family Feedly Summary: After many months of previews, Gemini 2.5 Pro and Flash have reached general availability with new, memorable model IDs: gemini-2.5-pro and gemini-2.5-flash. They are joined by a new preview model with an unmemorable name: gemini-2.5-flash-lite-preview-06-17 is a…
-
Bulletins: Vulnerability Summary for the Week of June 9, 2025
Source URL: https://www.cisa.gov/news-events/bulletins/sb25-167 Source: Bulletins Title: Vulnerability Summary for the Week of June 9, 2025 Feedly Summary: High Vulnerabilities PrimaryVendor — Product Description Published CVSS Score Source Info Acer–ControlCenter Acer ControlCenter contains Remote Code Execution vulnerability. The program exposes a Windows Named Pipe that uses a custom protocol to invoke internal functions. However, this Named…
-
Simon Willison’s Weblog: The lethal trifecta for AI agents: private data, untrusted content, and external communication
Source URL: https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/#atom-everything Source: Simon Willison’s Weblog Title: The lethal trifecta for AI agents: private data, untrusted content, and external communication Feedly Summary: If you are a user of LLM systems that use tools (you can call them “AI agents" if you like) it is critically important that you understand the risk of combining tools…
-
Simon Willison’s Weblog: An Introduction to Google’s Approach to AI Agent Security
Source URL: https://simonwillison.net/2025/Jun/15/ai-agent-security/#atom-everything Source: Simon Willison’s Weblog Title: An Introduction to Google’s Approach to AI Agent Security Feedly Summary: Here’s another new paper on AI agent security: An Introduction to Google’s Approach to AI Agent Security, by Santiago Díaz, Christoph Kern, and Kara Olive. (I wrote about a different recent paper, Design Patterns for Securing…
-
Simon Willison’s Weblog: Anthropic: How we built our multi-agent research system
Source URL: https://simonwillison.net/2025/Jun/14/multi-agent-research-system/#atom-everything Source: Simon Willison’s Weblog Title: Anthropic: How we built our multi-agent research system Feedly Summary: Anthropic: How we built our multi-agent research system OK, I’m sold on multi-agent LLM systems now. I’ve been pretty skeptical of these until recently: why make your life more complicated by running multiple different prompts in parallel…