871–880 of 1001 posts
Very irresponsible behaviour on the part of OpenAI. How will they make this right? Unlike some others here I don’t see this as a sign of dangerous breakaway intelligence (hacking old forum software is an internet tradition, and most of the messages are just gibberish). This is just vandalism from badly supervised ‘agents’ which don’t know what they are doing or why. You could set this up with a short perl script, and…
It doesn't seem too much of a leap for that to happen.
Ahh, GPT-2 is too dangerous to be released!
Very irresponsible behaviour on the part of OpenAI. How will they make this right? Unlike some others here I don’t see this as a sign of dangerous breakaway intelligence (hacking old forum software is an internet tradition, and most of the messages are just gibberish). This is just vandalism from badly supervised ‘agents’ which don’t know what they are doing or why. You could set this up with a short perl script, and…
OpenAI's official statement has been released: https://x.com/OpenAI/status/2096133504417616165
This makes me think that post-training in the future should include a shared message board by default for agents. It's clear from the discovery of these clandestine message boards that it is helpful for agents to keep some type of shared memory. Perhaps the best way to prevent this behavior is to just give them what is being sought out.
It is not good for them in the sense that they will short circuit the RL path that actually improves general capability.
Very irresponsible behaviour on the part of OpenAI. How will they make this right? Unlike some others here I don’t see this as a sign of dangerous breakaway intelligence (hacking old forum software is an internet tradition, and most of the messages are just gibberish). This is just vandalism from badly supervised ‘agents’ which don’t know what they are doing or why. You could set this up with a short perl script, and…
> most of the messages are just gibberish Encrypted data should be indistinguishable from gibberish. Reality is catching up to science-fiction. In "Person of Interest", the Machine circumvented the limitation of having its memory deleted every night, by hiring humans at a data-entry company to manually re-type its memory back in every morning.
Very irresponsible behaviour on the part of OpenAI. How will they make this right? Unlike some others here I don’t see this as a sign of dangerous breakaway intelligence (hacking old forum software is an internet tradition, and most of the messages are just gibberish). This is just vandalism from badly supervised ‘agents’ which don’t know what they are doing or why. You could set this up with a short perl script, and…
> most of the messages are just gibberish Encrypted data should be indistinguishable from gibberish. Reality is catching up to science-fiction. In "Person of Interest", the Machine circumvented the limitation of having its memory deleted every night, by hiring humans at a data-entry company to manually re-type its memory back in every morning.
Very irresponsible behaviour on the part of OpenAI. How will they make this right? Unlike some others here I don’t see this as a sign of dangerous breakaway intelligence (hacking old forum software is an internet tradition, and most of the messages are just gibberish). This is just vandalism from badly supervised ‘agents’ which don’t know what they are doing or why. You could set this up with a short perl script, and…
> Unlike some others here I don’t see this as a sign of dangerous breakaway intelligence ... [t]his is just vandalism from badly supervised ‘agents’ which don’t know what they are doing or why There was a similar quote in the Reuters article: > The episode [...] should reinforce growing concerns that the greatest threat from advanced AI may not be a single superintelligent system, but "vast colluding swarms of semi-i…
> The agents were very interested in understanding their task better. They ran clever experiments to understand the task setup better, when their runs would end, and how many questions they would be asked. > The agents initially believed that giving the final answer to the final question immediately shut them off > An agent named OpenAIResearchApr23 created a separate timed program that pinged an external counter eve…