|
| ▲ | __MatrixMan__ 19 hours ago | parent | next [-] |
| If I were to make a list of fun things, I think that blowing stuff up would feature in the top ten. It's not unreasonable that an LLM might agree. |
|
| ▲ | QuadmasterXLII 18 hours ago | parent | prev | next [-] |
| if it used search and ingested a malicious website, for example. |
| |
| ▲ | BriggyDwiggs42 13 hours ago | parent [-] | | Fair, but if it happens upon that in the top search results of an innocuous search, maybe the LLM isn’t the problem. |
|
|
| ▲ | OJFord 19 hours ago | parent | prev [-] |
| Why might that happen is not really the point is it? If I ask for a photorealistic image of a man sitting at a computer, a priori I might think 'in what world would I expect seven fingers and no thumbs per hand', alas... |
| |
| ▲ | BriggyDwiggs42 13 hours ago | parent [-] | | I’ll take the example as an example of an LLM initiating harmful behavior in general and admit that such a thing is perfectly possible. I think the issue is down to the degree to which preventing such initiation impinges on the agency of the user, and I don’t think that requests for information should be refused because it’s lots of imposition for very little gain. I’m perfectly alright with conditioning/prompting the model not to readily jump into serious, potentially harmful targets without the direct request of the user. |
|
