Viewing profile — alexbecker

I'm working on _prompt injection_, the problem where LLMs can't reliably distinguish between the user's instructions and untrusted content like web search results. Just published a…

Generally the threat model is that a trusted user is trying to get untrusted data into the system. E.g. you have an email monitor that reads your emails and takes certain actions f…

There have been attempts like https://arxiv.org/pdf/2410.09102 to do this kind of color-coding but none of them work in a multi-turn context since as you note you can't trust the p…

The problem is there is no real way to separate "data" and "instructions" in LLMs like there is for SQL

I doubt Comet was using any protections beyond some tuned instructions, but one thing I learned at USENIX Security a couple weeks ago is that nobody has any idea how to deal with p…

Lately I've been trying to detect/mitigate prompt injection attacks. Wrote a blog post about why it's hard: https://alexcbecker.net/blog/prompt-injection.html

I struggle with actually speaking to people in languages I'm learning, and as a result I don't practice it much and don't get better at it. So I built an AI platform to let me prac…

After reading Judith Butler for a class in college, reading "Professor of Parody" was such a breath of fresh air. Nussbaum is a clear thinker who doesn't take BS kindly.

The argument as I understand it is that group 2 mostly does not care about being protected from their government or even agrees with the government's actions, and they get to benef…

I run a similar, maybe even more boring stack for my less-than-one-person company [PyDist]( https://pydist.com ): - PostgreSQL database - Nginx proxy in front of Django apps for UI…

My team currently uses Confluence (an Atlassian product) for requirements, designs, procedures, and for various other engineering and product-related documents. However, I find it …

Running a python package registry has some unique challenges, so it makes sense not to start with it (I run such a registry: https://pydist.com ). For example, Python has a distinc…

At my company, we use Slack (and email) for messaging, Jira for project management and Confluence to plan and document. But I'm not very satisfied with them, especially Confluence,…

DevPi is a good solution if you want to self-host a Python package index. PyDist has some additional features like API keys and download statistics which I think are nice, but the …

Why would you not expect someone to charge for this? There are many services that charge for hosting private packages (rather than making them public to the world); I'm not aware o…

Yes, you can use --index-url. I assume you're referring to how --extra-index-url means that pip will randomly choose which index to try to install from, potentially installing a pu…

It's worth pointing out that while modern hash functions are believed to be infeasible to unscramble (technically, to require exponential time), none have been proven so. In fact, …