Simon Willison’s Weblog

Subscribe
Atom feed for swyx

5 items tagged “swyx”

2023

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 / openai, ai, llms, prompt-engineering, prompt-injection, swyx, generative-ai, chatgpt

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 / swyx, generative-ai, chatgpt, ai, llms, speaking, podcasts, code-interpreter

2022

Reverse Prompt Engineering for Fun and (no) Profit (via) swyx pulls off some impressive prompt leak attacks to reverse engineer the new AI features that just got added to Notion. He concludes that “Prompts are like clientside JavaScript. They are shipped as part of the product, but can be reverse engineered easily, and the meaningful security attack surface area is exactly the same.”

# 28th December 2022, 8:56 pm / swyx, prompt-engineering, prompt-injection, gpt-3, llms, generative-ai

Of all the parameters in SD, the seed parameter is the most important anchor for keeping the image generation the same. In SD-space, there are only 4.3 billion possible seeds. You could consider each seed a different universe, numbered as the Marvel universe does (where the main timeline is #616, and #616 Dr Strange visits #838 and a dozen other universes). Universe #42 is the best explored, because someone decided to make it the default for text2img.py (probably a Hitchhiker’s Guide reference). But you could change the seed, and get a totally different result from what is effectively a different universe.

swyx

# 17th September 2022, 9:02 pm / stable-diffusion, prompt-engineering, ai, swyx

The End of Localhost. swyx makes the argument for cloud-based development environments, and points out that many large companies—including Google, Facebook, Shopify and GitHub—have made the move already. I was responsible for the team maintaining the local development environment experience at Eventbrite for a while, and my conclusion is that with a large enough engineering team someone will ALWAYS find a new way to break their local environment: the idea of being able to bootstrap a fresh, guaranteed-to-work environment in the cloud at the click of a button could save SO much time and money.

# 8th June 2022, 6:09 pm / software-engineering, swyx