Simon Willison’s Weblog

Subscribe

Friday, 14th April 2023

Building LLM applications for production. Chip Huyen provides a useful, in-depth review of the challenges involved in taking an app built on top of a LLM from prototype to production, including issues such as prompt ambiguity and unpredictability, cost and latency concerns, challenges in testing and updating to new models. She also lists some promising use-cases she’s seeing for categories of application built on these tools.

# 3:35 pm / ai, prompt-engineering, generative-ai, llms

Prompt injection: What’s the worst that can happen?

Visit Prompt injection: What's the worst that can happen?

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.

[... 2,302 words]

One way to avoid unspotted prediction errors is for the technology in its current state to have early and frequent contact with reality as it is iteratively developed, tested, deployed, and all the while improved. And there are creative ideas people don’t often discuss which can improve the safety landscape in surprising ways — for example, it’s easy to create a continuum of incrementally-better AIs (such as by deploying subsequent checkpoints of a given training run), which presents a safety opportunity very unlike our historical approach of infrequent major model upgrades.

Greg Brockman

# 6:08 pm / ai, openai, generative-ai, llms

New prompt injection attack on ChatGPT web version. Markdown images can steal your chat data. An ingenious new prompt injection / data exfiltration vector from Roman Samoilenko, based on the observation that ChatGPT can render markdown images in a way that can exfiltrate data to the image hosting server by embedding it in the image URL. Roman uses a single pixel image for that, and combines it with a trick where copy events on a website are intercepted and prompt injection instructions are appended to the copied text, in order to trick the user into pasting the injection attack directly into ChatGPT.

Update: They finally started mitigating this in December 2023.

# 6:33 pm / security, ai, prompt-engineering, prompt-injection, generative-ai, chatgpt, llms, markdown-exfiltration

codespaces-jupyter (via) This is really neat. Click “Use this template” -> “Open in a codespace” and you get a full in-browser VS Code interface where you can open existing notebook files (or create new ones) and start playing with them straight away.

# 10:38 pm / github, python, jupyter, github-codespaces