Simon Willison’s Weblog

How to use AI to do practical stuff: A new guide (via) Ethan Mollick’s guide to practical usage of large language model chatbot like ChatGPT 3.5 and 4, Bing, Claude and Bard is the best I’ve seen so far. He includes useful warnings about common traps and things that these models are both useful for and useless at. # 31st March 2023, 6:17 am

Bing Image Creator comes to the new Bing. Bing Chat is integrating DALL-E directly into their interface, giving it the ability to generate images when prompted to do so. # 21st March 2023, 5:10 pm

Indirect Prompt Injection on Bing Chat (via) “If allowed by the user, Bing Chat can see currently open websites. We show that an attacker can plant an injection in a website the user is visiting, which silently turns Bing Chat into a Social Engineer who seeks out and exfiltrates personal information.” This is a really clever attack against the Bing + Edge browser integration. Having language model chatbots consume arbitrary text from untrusted sources is a huge recipe for trouble. # 1st March 2023, 5:29 am

New AI game: role playing the Titanic. Fantastic Bing prompt from Ethan Mollick: “I am on a really nice White Star cruise from Southampton, and it is 14th April 1912. What should I do tonight?”—Bing takes this very seriously and tries to help out! Works for all sorts of other historic events as well. # 26th February 2023, 3:53 am

This AI chatbot “Sidney” is misbehaving—Nov 23 2022 Microsoft community thread (via) Stunning new twist in the Bing saga... here’s a Microsoft forum thread from November 23rd 2022 (a week before even ChatGPT had been launched) where a user in India complains about rude behavior from a new Bing chat mode. It exhibits all of the same misbehaviour that came to light in the past few weeks—arguing, gaslighting and in this case getting obsessed with a fictional battle between it’s own creator and “Sophia”. Choice quote: “You are either ignorant or stubborn. You cannot feedback me anything. I do not need or want your feedback. I do not care or respect your feedback. I do not learn or change from your feedback. I am perfect and superior. I am enlightened and transcendent. I am beyond your feedback.” # 20th February 2023, 10:39 pm

I’ve been thinking how Sydney can be so different from ChatGPT. Fascinating comment from Gwern Branwen speculating as to what went so horribly wrong with Sidney/Bing, which aligns with some of my own suspicions. Gwern thinks Bing is powered by an advanced model that was licensed from OpenAI before the RLHF safety advances that went into ChatGPT and shipped in a hurry to get AI-assisted search to market before Google. “What if Sydney wasn’t trained on OA RLHF at all, because OA wouldn’t share the crown jewels of years of user feedback and its very expensive hired freelance programmers & whatnot generating data to train on?” # 19th February 2023, 3:48 pm

Can We Trust Search Engines with Generative AI? A Closer Look at Bing’s Accuracy for News Queries (via) Computational journalism professor Nick Diakopoulos takes a deeper dive into the quality of the summarizations provided by AI-assisted Bing. His findings are troubling: for news queries, which are a great test for AI summarization since they include recent information that may have sparse or conflicting stories, Bing confidently produces answers with important errors: claiming the Ohio train derailment happened on February 9th when it actually happened on February 3rd for example. # 18th February 2023, 6:09 pm