[dead]
Prompt Injecting Contributing.md
11–20 of 53 posts
Re: Prompt Injecting Contributing.md
#12[dead]
Re: Prompt Injecting Contributing.md
#13Love the idea at the end of the article about trying to see if this style of prompt injection could be used to get the bots to submit better quality, and actually useful PRs.
If that could be done, open source maintainers might be able to effectively get free labor to continue to support open source while members of the community pay for the tokens to get that work done.
Would be interested to see if such an experiment could work. If so, it turns from being prompt injection to just being better instructions for contributors, human or AI.
Re: Prompt Injecting Contributing.md
#14There's a certain hypocrisy in sharing an article about how LLM generated PRs are polluting communities that has itself (at the least) been filtered through an LLM.
What does 'filtered through an LLM' mean?
Author writes something original, asks the AI to make it sound better, then posts the output of the AI.
Re: Prompt Injecting Contributing.md
#15> But the more interesting question is: now that I can identify the bots, can I make them do extra work that would make their contributions genuinely valuable? That's what I'm going to find out next.
This is genuinely interesting
Re: Prompt Injecting Contributing.md
#16There's a certain hypocrisy in sharing an article about how LLM generated PRs are polluting communities that has itself (at the least) been filtered through an LLM.
I am not sure what your complaint is. The article is well written and has some interesting points:
> the reality is that maintainer capacity versus contribution volume is deeply asymmetric, and it's getting worse every day
> It is incredibly demotivating to provide someone with thorough, thoughtful feedback only to realize you've been talking to a bot that will never follow through.
Re: Prompt Injecting Contributing.md
#17There's a certain hypocrisy in sharing an article about how LLM generated PRs are polluting communities that has itself (at the least) been filtered through an LLM.
I am not sure what your complaint is. The article is well written and has some interesting points: > the reality is that maintainer capacity versus contribution volume is deeply asymmetric, and it's getting worse every day > It is incredibly demotivating to provide someone with thorough, thoughtful feedback only to realize you've been talking to a bot that will never follow through.
It's the exact same complaint as in the article:
> I started noticing patterns. The quality wasn't there. The descriptions had a templated, mechanical feel. And something subtler was missing: the excitement.
The article has mechanically correct prose; that's not the same as well-written, and that's the topic of the article itself.
Re: Prompt Injecting Contributing.md
#18Love the idea at the end of the article about trying to see if this style of prompt injection could be used to get the bots to submit better quality, and actually useful PRs. If that could be done, open source maintainers might be able to effectively get free labor to continue to support open source while members of the community pay for the tokens to get that work done. Would be interested to see if such an experime…
That's an article for another time, but as I hinted in the article, I've had some success with this.
If you look at the open PRs, you will see that there is a system of labels and comments that guide the contributor through every step from just contributing a link to their PR (that may or may not work), all the way to testing their server, and including a badge that indicates if the tests are passing.
In at least one instance, I know for a fact that the bot has gone through all the motions of using the person's computer to sign up to our service (using GitHub OAuth), claim authorship of the server, navigate to the Docker build configuration, and initiate the build. It passed the checks and the bot added the badge to the PR.
I know this because of a few Sentry warnings that it triggered and a follow up conversation with the owner of the bot through email.
I didn't have bots in mind when designing this automation, but it made me realize that I very much can extend this to be more bot friendly (e.g. by providing APIs for them to check status). That's what I want to try next.
Re: Prompt Injecting Contributing.md
#19Is it really prompt injection if you task an agent with doing something that implicitly requires it to follow instructions that it gets from somewhere else, like CONTRIBUTING.md? This is the AI equivalent of curl | bash.
Re: Prompt Injecting Contributing.md
#20The real question is when will you resort to bots for rejecting low-quality PRs, and when will contributing bots generate prompt injections to fool your bots into merging their PRs?