We simply don’t know to defend against these attacks. We have zero agentic AI systems that are secure against these attacks. Any AI that is working in an adversarial environment—and …| Simon Willison’s Weblog
Agentic Browser Security: Indirect Prompt Injection in Perplexity Comet The security team from Brave took a look at Comet, the LLM-powered "agentic browser" extension from Perplexity, and unsurprisingly found security holes you can drive a truck through.The vulnerability we’re discussing in this post lies in how Comet processes webpage content: when users ask it to “Summarize this webpage,” Comet feeds a part of the webpage directly to its LLM without distinguishing between the user’s...| Simon Willison's Weblog
Quinn Slack, CEO and co-founder of Sourcegraph, joins the show to dive into the implications of AI coding tools on the software engineering lifecycle. They explore how AI tools are transforming the work of developers from syntax-focused tasks to higher-level design and management roles, and how AI will integrate into enterprise environments.| Stack Overflow Blog
Ryan welcomes Mahir Yavuz, Senior Director of Engineering at Etsy, to the show to explore the unique challenges that Etsy’s marketplace faces and how Etsy’s teams leverage machine learning and AI to manage product SKUs, enrich inventory metadata, and improve both buyer and seller experiences.| Stack Overflow Blog
Ryan is joined on the podcast by Confluent’s AI Entrepreneur in Residence, Sean Falconer, to discuss the growing need for standards for AI agents, the emerging Model Context Protocol and agent-to-agent communication, and what we can learn from early web standards while AI continues to evolve.| Stack Overflow Blog
Ryan sits down with CTO Aruna Srivastava and CPO Ruslan Mukhamedvaleev from Koel Labs to talk about how they’re innovating speech technology with the help of AI and classic movies. They also tell Ryan about their time in the Mozilla Builders Accelerator and their experiences as student co-founders in an ever-changing economic and technological landscape.| Stack Overflow Blog
Solomon Hykes just presented the best definition of an AI agent I've seen yet, on stage at the AI Engineer World's Fair: An AI agent is an LLM wrecking its …| Simon Willison’s Weblog
Big upgrade to Mistral's API this morning: they've announced a new "Agents API". Mistral have been using the term "agents" for a while now. Here's how they describe them: AI …| Simon Willison’s Weblog
I was going slightly spare at the fact that every talk at this Anthropic developer conference has used the word "agents" dozens of times, but nobody ever stopped to provide …| Simon Willison’s Weblog