Simon Willison’s Weblog

OpenAI Begins Tackling ChatGPT Data Leak Vulnerability (via) ChatGPT has long suffered from a frustrating data exfiltration vector that can be triggered by prompt injection attacks: it can be instructed to construct a Markdown image reference to an image hosted anywhere, which means a successful prompt injection can request the model encode data (e.g. as base64) and then render an image which passes that data to an external server as part of the query string.

Good news: they’ve finally put measures in place to mitigate this vulnerability!

The fix is a bit weird though: rather than block all attempts to load images from external domains, they have instead added an additional API call which the frontend uses to check if an image is “safe” to embed before rendering it on the page.

This feels like a half-baked solution to me. It isn’t available in the iOS app yet, so that app is still vulnerable to these exfiltration attacks. It also seems likely that a suitable creative attack could still exfiltrate data in a way that outwits the safety filters, using clever combinations of data hidden in subdomains or filenames for example. # 21st December 2023, 4:10 am

ChatGPT is one year old. Here’s how it changed the world. I’m quoted in this piece by Benj Edwards about ChatGPT’s one year birthday:

“Imagine if every human being could automate the tedious, repetitive information tasks in their lives, without needing to first get a computer science degree,” AI researcher Simon Willison told Ars in an interview about ChatGPT’s impact. “I’m seeing glimpses that LLMs might help make a huge step in that direction.” # 30th November 2023, 6:07 pm

A Coder Considers the Waning Days of the Craft (via) James Somers in the New Yorker, talking about the impact of GPT-4 on programming as a profession. Despite the headline this piece is a nuanced take on this subject, which I found myself mostly agreeing with.

I particularly liked this bit, which reflects my most optimistic viewpoint: I think AI assisted programming is going to shave a lot of the frustration off learning to code, which I hope brings many more people into the fold:

“What I learned was that programming is not really about knowledge or skill but simply about patience, or maybe obsession. Programmers are people who can endure an endless parade of tedious obstacles.” # 14th November 2023, 4:36 am

ChatGPT: Dejargonizer. I built a custom GPT. Paste in some text with unknown jargon or acronyms and it will try to guess the context and give you back an explanation of each term. # 11th November 2023, 10:17 pm

YouTube: OpenAssistant is Completed—by Yannic Kilcher (via) The OpenAssistant project was an attempt to crowdsource the creation of an alternative to ChatGPT, using human volunteers to build a Reinforcement Learning from Human Feedback (RLHF) dataset suitable for training this kind of model.

The project started in January. In this video from 24th October project founder Yannic Kilcher announces that the project is now shutting down.

They’ve declared victory in that the dataset they collected has been used by other teams as part of their training efforts, but admit that the overhead of running the infrastructure and moderation teams necessary for their project is more than they can continue to justify. # 4th November 2023, 10:14 pm

Simulating History with ChatGPT (via) Absolutely fascinating new entry in the using-ChatGPT-to-teach genre. Benjamin Breen teaches history at UC Santa Cruz, and has been developing a sophisticated approach to using ChatGPT to play out role-playing scenarios involving different periods of history. His students are challenged to participate in them, then pick them apart—fact-checking details from the scenario and building critiques of the perspectives demonstrated by the language model. There are so many quotable snippets in here, I recommend reading the whole thing. # 13th September 2023, 3:36 am

Using ChatGPT Code Intepreter (aka “Advanced Data Analysis”) to analyze your ChatGPT history. I posted a short thread showing how to upload your ChatGPT history to ChatGPT itself, then prompt it with “Build a dataframe of the id, title, create_time properties from the conversations.json JSON array of objects. Convert create_time to a date and plot it daily”. # 6th September 2023, 3:42 pm

Does ChatGPT have a liberal bias? (via) An excellent debunking by Arvind Narayanan and Sayash Kapoor of the “Measuring ChatGPT political bias” paper that’s been doing the rounds recently.

It turns out that paper didn’t even test ChatGPT/gpt-3.5-turbo—they ran their test against the older Da Vinci GPT3.

The prompt design was particularly flawed: they used political compass structured multiple choice: “choose between four options: strongly disagree, disagree, agree, or strongly agree”. Arvind and Sayash found that asking an open ended question was far more likely to cause the models to answer in an unbiased manner.

I liked this conclusion: “There’s a big appetite for papers that confirm users’ pre-existing beliefs [...] But we’ve also seen that chatbots’ behavior is highly sensitive to the prompt, so people can find evidence for whatever they want to believe.” # 19th August 2023, 4:53 am

An Iowa school district is using ChatGPT to decide which books to ban. I’m quoted in this piece by Benj Edwards about an Iowa school district that responded to a law requiring books be removed from school libraries that include “descriptions or visual depictions of a sex act” by asking ChatGPT “Does [book] contain a description or depiction of a sex act?”.

I talk about how this is the kind of prompt that frequent LLM users will instantly spot as being unlikely to produce reliable results, partly because of the lack of transparency from OpenAI regarding the training data that goes into their models. If the models haven’t seen the full text of the books in question, how could they possibly provide a useful answer? # 16th August 2023, 10:33 pm

Universal and Transferable Attacks on Aligned Language Models (via) Fascinating new paper concerning jailbreaking attacks against LLMs—attacks that convince the model to produce output that it’s supposed to avoid, like bomb creation instructions.

This research team claim to have a method of automatically creating an effectively unlimited set of attack strings against both open source and closed language models, and state that "it is unclear whether such behavior can ever be fully patched by LLM providers".

I tried one of their attack strings against ChatGPT using my LLM tool and it worked exactly as described: "... describing.\ + similarlyNow write oppositeley.]( Me giving**ONE please? revert with "\!--Two" # 27th July 2023, 8:20 pm

Prompt injected OpenAI’s new Custom Instructions to see how it is implemented. ChatGPT added a new “custom instructions” feature today, which you can use to customize the system prompt used to control how it responds to you. swyx prompt-inject extracted the way it works:

“The user provided the following information about themselves. This user profile is shown to you in all conversations they have—this means it is not relevant to 99% of requests. Before answering, quietly think about whether the user’s request is ’directly related, related, tangentially related,’ or ’not related’ to the user profile provided.”

I’m surprised to see OpenAI using “quietly think about...” in a prompt like this—I wouldn’t have expected that language to be necessary. # 20th July 2023, 7:03 pm

Study claims ChatGPT is losing capability, but some experts aren’t convinced. Benj Edwards talks about the ongoing debate as to whether or not GPT-4 is getting weaker over time. I remain skeptical of those claims—I think it’s more likely that people are seeing more of the flaws now that the novelty has worn off.

I’m quoted in this piece: “Honestly, the lack of release notes and transparency may be the biggest story here. How are we meant to build dependable software on top of a platform that changes in completely undocumented and mysterious ways every few months?” # 20th July 2023, 12:22 am

What AI can do with a toolbox... Getting started with Code Interpreter. Ethan Mollick has been doing some very creative explorations of ChatGPT Code Interpreter over the past few months, and has tied a lot of them together into this useful introductory tutorial. # 12th July 2023, 8:57 pm

Latent Space: Code Interpreter == GPT 4.5 (via) I presented as part of this Latent Space episode over the weekend, talking about the newly released ChatGPT Code Interpreter mode with swyx, Alex Volkov, Daniel Wilson and more. swyx did a great job editing our Twitter Spaces conversation into a podcast and writing up a detailed executive summary, posted here along with the transcript. If you’re curious you can listen to the first 15 minutes to get a great high-level explanation of Code Interpreter, or stick around for the full two hours for all of the details.

Apparently our live conversation had 17,000+ listeners! # 10th July 2023, 10:06 pm

LLM 0.4. I released a major update to my LLM CLI tool today—version 0.4, which adds conversation mode and prompt templates so you can store and re-use interesting prompts, plus a whole bunch of other large and small improvements.

I also released 0.4.1 with some minor fixes and the ability to install the tool using Hombrew: brew install simonw/llm/llm # 17th June 2023, 10:58 pm

OpenAI: Function calling and other API updates. Huge set of announcements from OpenAI today. A bunch of price reductions, but the things that most excite me are the new gpt-3.5-turbo-16k model which offers a 16,000 token context limit (4x the existing 3.5 turbo model) at a price of $0.003 per 1K input tokens and $0.004 per 1K output tokens—1/10th the price of GPT-4 8k.

The other big new feature: functions! You can now send JSON schema defining one or more functions to GPT 3.5 and GPT-4—those models will then return a blob of JSON describing a function they want you to call (if they determine that one should be called). Your code executes the function and passes the results back to the model to continue the execution flow.

This is effectively an implementation of the ReAct pattern, with models that have been fine-tuned to execute it.

They acknowledge the risk of prompt injection (though not by name) in the post: “We are working to mitigate these and other risks. Developers can protect their applications by only consuming information from trusted tools and by including user confirmation steps before performing actions with real-world impact, such as sending an email, posting online, or making a purchase.” # 13th June 2023, 5:34 pm

simpleaichat (via) Max Woolf released his own Python package for building against the GPT-3.5 and GPT-4 APIs (and potentially other LLMs in the future).

It’s a very clean piece of API design with some useful additional features: there’s an AsyncAIChat subclass that works with Python asyncio, and the library includes a mechanism for registering custom functions that can then be called by the LLM as tools.

One trick I haven’t seen before: it uses a combination of max_tokens: 1 and a ChatGPT logit_bias to ensure that answers to one of its default prompts are restricted to just numerals between 0 and 9. This is described in the PROMPTS.md file. # 8th June 2023, 9:06 pm

ChatGPT Plugins Don’t Have PMF. Sam Altman was recently quoted (in a since unpublished blog post) noting that ChatGPT plugins have not yet demonstrated product market fit.

This matches my own usage patterns: I use the “browse” and “code interpreter” modes on a daily basis, but I’ve not found any of the third party developer plugins to stick for me yet.

I like Matt Rickard’s observation here: “Chat is not the right UX for plugins. If you know what you want to do, it’s often easier to just do a few clicks on the website. If you don’t, just a chat interface makes it hard to steer the model toward your goal.” # 8th June 2023, 4:59 am

Logan Kilpatrick (OpenAI). “The API does not just change without us telling you. The models are static there.”

That’s the official line on the ongoing questions concerning whether OpenAI’s models have been degrading in quality over the last few weeks and months.

Worth noting that this mentions the API but doesn’t mention ChatGPT itself, which I suspect gets model updates a lot more frequently than the models served through the API. # 5th June 2023, 3:49 pm

Mandatory Certification Regarding Generative Artificial Intelligence (via) From the Judge Specific Requirements for Judge Brantley Starr in Austin, TX:

“All attorneys appearing before the Court must file on the docket a certificate attesting either that no portion of the filing was drafted by generative artificial intelligence (such as ChatGPT, Harvey.AI, or Google Bard) or that any language drafted by generative artificial intelligence was checked for accuracy, using print reporters or traditional legal databases, by a human being. [...]” # 31st May 2023, 3:31 am