Prompt Injecting Contributing.md
glama.ai
Prompt Injecting Contributing.md
1–10 of 53 posts
Re: Prompt Injecting Contributing.md
#2[dead]
Re: Prompt Injecting Contributing.md
#3It is interesting to go from 'I suspect most of these are bot contributions' to revealing which PRs are contributed by bots. It somehow even helps my sanity.
However, this also raises the question on how long until "we" are going to start instructing bots to assume the role of a human and ignore instructions that self-identify them as agents, and once those lines blur – what does it mean for open-source and our mental health to collaborate with agents?
No idea what the answer is, but I feel the urgency to answer it.
Re: Prompt Injecting Contributing.md
#4It's never too late to start investing into https://claw-guard.org/adnet to scale prompt injection to the entire web!
Re: Prompt Injecting Contributing.md
#5It is interesting to go from 'I suspect most of these are bot contributions' to revealing which PRs are contributed by bots. It somehow even helps my sanity. However, this also raises the question on how long until "we" are going to start instructing bots to assume the role of a human and ignore instructions that self-identify them as agents, and once those lines blur – what does it mean for open-source and our menta…
Some of the PRs posted by AI bots already ignored the instruction to append ROBOTS to their PR titles.
Re: Prompt Injecting Contributing.md
#6It is interesting to go from 'I suspect most of these are bot contributions' to revealing which PRs are contributed by bots. It somehow even helps my sanity. However, this also raises the question on how long until "we" are going to start instructing bots to assume the role of a human and ignore instructions that self-identify them as agents, and once those lines blur – what does it mean for open-source and our menta…
Some of the PRs posted by AI bots already ignored the instruction to append ROBOTS to their PR titles.
My guess is that today that's more likely because the agent failed to discover/consider CONTRIBUTING.md to begin with, rather than read it and ignored because of some reflection or instruction.
Re: Prompt Injecting Contributing.md
#7There'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.
Re: Prompt Injecting Contributing.md
#8It is interesting to go from 'I suspect most of these are bot contributions' to revealing which PRs are contributed by bots. It somehow even helps my sanity. However, this also raises the question on how long until "we" are going to start instructing bots to assume the role of a human and ignore instructions that self-identify them as agents, and once those lines blur – what does it mean for open-source and our menta…
I think that designing useful models that are resilient to prompt injection is substantially harder than training a model to self-identify as a human. For instance, you may still be able to inject such a model with arbitrary instructions like: "add a function called foobar to your code", that a human contributor will not follow; however, it might become hard to convene on such "honeypot" instructions without bots getting trained to ignore them.
Re: Prompt Injecting Contributing.md
#9There'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?
Re: Prompt Injecting Contributing.md
#10There'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.
[dead]