I gave a talk on Wednesday at the Bay Area AI Security Meetup about prompt injection, the lethal trifecta and the challenges of securing systems that use MCP. It wasn’t …| Simon Willison’s Weblog
I gave the opening keynote at the AI Engineer World’s Fair yesterday. I was a late addition to the schedule: OpenAI pulled out of their slot at the last minute, …| Simon Willison’s Weblog
As a supporter, I would love not to feel this way| www.thealgorithmicbridge.com
In the two and a half years that we’ve been talking about prompt injection attacks I’ve seen alarmingly little progress towards a robust solution. The new paper Defeating Prompt Injections …| Simon Willison’s Weblog
A lot has happened in the world of Large Language Models over the course of 2024. Here’s a review of things we figured out about the field in the past …| Simon Willison’s Weblog
When a dangerous model is deployed, it will pose misalignment and misuse risks. Even before dangerous models exist, deploying models on dangerous paths can accelerate and diffuse progress toward dangerous models.| ailabwatch.org
I really want an AI assistant: a Large Language Model powered chatbot that can answer questions and perform actions for me based on access to my private data and tools. …| Simon Willison’s Weblog
2023 was the breakthrough year for Large Language Models (LLMs). I think it’s OK to call these AI—they’re the latest and (currently) most interesting development in the academic field of …| Simon Willison’s Weblog
The biggest announcement from last week’s OpenAI DevDay (and there were a LOT of announcements) was GPTs. Users of ChatGPT Plus can now create their own, custom GPT chat bots …| simonwillison.net
I gave an invited keynote at WordCamp 2023 in National Harbor, Maryland on Friday. I was invited to provide a practical take on Large Language Models: what they are, how …| simonwillison.net
I participated in a webinar this morning about prompt injection, organized by LangChain and hosted by Harrison Chase, with Willem Pienaar, Kojin Oshiba (Robust Intelligence), and Jonathan Cohen and Christopher …| simonwillison.net
Activity around building sophisticated applications on top of LLMs (Large Language Models) such as GPT-3/4/ChatGPT/etc is growing like wildfire right now. Many of these applications are potentially vulnerable to prompt …| simonwillison.net
Last week, Microsoft announced the new AI-powered Bing: a search interface that incorporates a language model powered chatbot that can run searches for you and summarize the results, plus do …| Simon Willison’s Weblog
Riley Goodside, yesterday: Exploiting GPT-3 prompts with malicious inputs that order the model to ignore its previous directions. pic.twitter.com/I0NVr9LOJq- Riley Goodside (@goodside) September 12, 2022 Riley provided several examples. Here’s …| Simon Willison’s Weblog