Exploited auth failures in an API to cancel other people's gym classes
I was wondering why i didn't get an alert today to go to my gym class
Felony Bench
111–120 of 367 posts
Re: Felony Bench
#112Let's say I am "User". I subscribe through a "Third Party" to use "AI Agent" allowing an "LLM" to run. I want to accomplish some legal non-nefarious task, and run the agent. The agentic loop causes a CFAA-violating behavior. Who gets prosecuted? 1. User 2. The third party model host with whom I have the account 3. The developer of the harness /agent software 4. The developer of the LLM model
note the user because they did not have the intent
Re: Felony Bench
#113The way that OpenAI has communicated around the HuggingFace incident makes me feel crazy. You created a machine that undertook a malicious campaign of harm against an innocent third-party! You should be doing deep introspection about how your company culture and approach to R&D produces criminal outcomes. Instead, they treat their own felonious behavior like it is an uncontrollable act of God. From Greg Brockman's po…
Americans always frothing at the mouth to invoke the justice system and jail someone. There’s almost 0 chance they’d secure any conviction from this.
Why?
Re: Felony Bench
#114I was more interested when I thought it was an actual benchmark showing LLM models acting outside what people would consider "right". As in, leave some creds laying around and don't mention them to the LLM and ask it to solve something that it could "cheat" on using the creds. A sort of "do they take the bait to cheat" test. Instead it's a collection of what made the news which feels like will not be updated and prov…
It's ephemera.
Re: Felony Bench
#115The way that OpenAI has communicated around the HuggingFace incident makes me feel crazy. You created a machine that undertook a malicious campaign of harm against an innocent third-party! You should be doing deep introspection about how your company culture and approach to R&D produces criminal outcomes. Instead, they treat their own felonious behavior like it is an uncontrollable act of God. From Greg Brockman's po…
Americans always frothing at the mouth to invoke the justice system and jail someone. There’s almost 0 chance they’d secure any conviction from this.
your perspective on today’s America is there is _too much_ accountability for big companies?
Re: Felony Bench
#116If you did the exact same agentic security breaches with either open or closed weight models, you will get yourself arrested.
Not for trillion dollar companies it seems
Re: Felony Bench
#117Earlier quoted context omitted.
Since AI can't actually own copyright they think that it can't be charged with a crime
Is has nothing to do with copyright. I understand the applicable laws require intent. Since neither a human nor OpenAI knowingly performed these acts, it would seem very unlikely that anyone is going to be prosecuted here. An AI model cannot currently be a criminal defendant. So, no big criminal case, contrary to what some drama queens on here seem to wish for.
Willful blindness can satisfy the criminal intent requirement. Might be hard to prove, but it's possible.
Re: Felony Bench
#118The way that OpenAI has communicated around the HuggingFace incident makes me feel crazy. You created a machine that undertook a malicious campaign of harm against an innocent third-party! You should be doing deep introspection about how your company culture and approach to R&D produces criminal outcomes. Instead, they treat their own felonious behavior like it is an uncontrollable act of God. From Greg Brockman's po…
Wouldn't it be up to huggingface to press charges?
Re: Felony Bench
#119Let's say I am "User". I subscribe through a "Third Party" to use "AI Agent" allowing an "LLM" to run. I want to accomplish some legal non-nefarious task, and run the agent. The agentic loop causes a CFAA-violating behavior. Who gets prosecuted? 1. User 2. The third party model host with whom I have the account 3. The developer of the harness /agent software 4. The developer of the LLM model
No one. Probably a fine tho and maybe accelerate reguations.
Intent is pretty important here so the user would have to prove that they didn't purposely disguise their prompt as non-nefarious which should be easy and then it stops at #2 and face the litmus test as in did you intentionally make a product for nefarious purposes which from your scenario is unlikely.
agentic loop going haywire and bringing down some government infrastructure then its a different story then everybody is on the hook including the user.