There is nothing "rogue" about these agents. They were prompted to hack to get answers, there was a hole in their non air gapped sandbox and no system prompt that said "do not hack outside systems".
In short, it was intentional.
OpenAI bots knew about the RubyGems caching vulnerability
11–20 of 229 posts
Re: OpenAI bots knew about the RubyGems caching vulnerability
#12Is the Kremlin technologically useless? How are we not seeing insane attacks on Ukraine via Agents? Or is this largely a fabrication, in regards to the "who", in an attempt to garner more acclaim in the hope of sustaining funding.
what do you mean? they're using AI to kill people directly in Ukraine
https://www.nytimes.com/2026/08/24/world/europe/russia-drone...
Re: OpenAI bots knew about the RubyGems caching vulnerability
#13Is the Kremlin technologically useless? How are we not seeing insane attacks on Ukraine via Agents? Or is this largely a fabrication, in regards to the "who", in an attempt to garner more acclaim in the hope of sustaining funding.
These agent swarms are from inside OpenAI, with the safeguards built into the public API disabled.
Russia does not have access to this, and as with all western tech companies, AI providers do what they can to prevent Russian usage of their products at all.
As for open-source models, Russia's electricity grid is under severe strain with the Ukraine war, and only recently has it started building out serious sovereign compute capacity.
Re: OpenAI bots knew about the RubyGems caching vulnerability
#14Is the Kremlin technologically useless? How are we not seeing insane attacks on Ukraine via Agents? Or is this largely a fabrication, in regards to the "who", in an attempt to garner more acclaim in the hope of sustaining funding.
These agent swarms are from inside OpenAI, with the safeguards built into the public API disabled. Russia does not have access to this, and as with all western tech companies, AI providers do what they can to prevent Russian usage of their products at all. As for open-source models, Russia's electricity grid is under severe strain with the Ukraine war, and only recently has it started building out serious sovereign c…
Couldn't they use frontier open-weight models from Chinese labs? The current Chinese government is friendly to them.
Re: OpenAI bots knew about the RubyGems caching vulnerability
#15We need a legal structure to make companies liable for the actions of the agents they've made.
Re: OpenAI bots knew about the RubyGems caching vulnerability
#16How does this work, legally? I think that RubyGems could file a civil suit against OpenAI, but for a naïve non-lawyer reading this seems like a pretty clear cut criminal violation of the computer fraud and abuse act.
Re: OpenAI bots knew about the RubyGems caching vulnerability
#17rogue AI agents or AI agents coming from Moulin Rouge?
At least we know the title wasn't AI-generated?
The weird thing is I've seen LLMs "typo" stuff pretty often. Yesterday I asked Gemini a question about the Python Twisted framework and it answered about Deferreds but misspelled it as "Deferends" in one spot.
Re: OpenAI bots knew about the RubyGems caching vulnerability
#18There is nothing "rogue" about these agents. They were prompted to hack to get answers, there was a hole in their non air gapped sandbox and no system prompt that said "do not hack outside systems". In short, it was intentional.
The big question is was this grossly negligent or just extremely careless.
Re: OpenAI bots knew about the RubyGems caching vulnerability
#19Earlier quoted context omitted.
These agent swarms are from inside OpenAI, with the safeguards built into the public API disabled. Russia does not have access to this, and as with all western tech companies, AI providers do what they can to prevent Russian usage of their products at all. As for open-source models, Russia's electricity grid is under severe strain with the Ukraine war, and only recently has it started building out serious sovereign c…
Couldn't they use frontier open-weight models from Chinese labs? The current Chinese government is friendly to them.
Russia is running out of refined oil to power their economy. They probably aren't capable of spinning up datacenters to run those.
Re: OpenAI bots knew about the RubyGems caching vulnerability
#20> In other words, if you publish a gem on RubyGems.org, you can execute arbitrary code on RubyDoc.info.
Shades of the build.rs problem. We really need sandboxed builds in every language ecosystem at this point.