| This is truly extraordinary 17:48 - Jul 22 with 2271 views | bsw72 |
Hugely significant event, where an autonomous AI agent hacked its way out of a supposedly secure sandbox environment to seek the answers to help it pass an evaluation.
https://www.theguardian.com/te |  | | |  |
| This is truly extraordinary on 21:57 - Jul 22 with 253 views | nodge_blue |
| This is truly extraordinary on 21:44 - Jul 22 by DanTheMan |
Musk says a lot of utter nonsense. |
Well that’s true but he was agreeing with my mate Geoffrey Hinton who I’m sure you got bored of me quoting last time. And when it comes to IT Musk is pretty good you know. |  |
| |
| This is truly extraordinary on 22:00 - Jul 22 with 238 views | StokieBlue |
| This is truly extraordinary on 20:08 - Jul 22 by DanTheMan |
It is incapable of thought, it's not thinking in the traditional sense of the term. I've equally seen a model literally today tell someone it couldn't hear him when he asked it a question. When asked whether it could hear him now it confirmed it couldn't.
There's a very funny thing you can do with some models where if you give it them this riddle but swap the genders, it cannot solve it. A similar one swaps a key word and the AI confidently ignores it.
https://open.substack.com/pub/
That's not to say these things are not clever tools, they are, and then can with enough time work out how to do things usually by brute force.
What's happened here is that it's been given a task to do something and it's worked out to get out of it's sandbox. That's it. This is an already known issue.
https://www.pillar.security/bl
I can give a really simple example. When developing I can sandbox an agent to not be allowed to say create files outside of a certain directory and if it tries, it will get blocked by the sandbox. Fantastic.
But what it could do, if I told it I wanted it to create a file where it shouldn't, is write a program to do it and run the program. And there we go, very simple sandbox broken.
This sounds very close to what OpenAI has described. It was asked to do something and on its way to doing it hit the sandbox and then found a vulnerability to use and did that.
And it was literally asked to do this kind of thing:
> This incident occurred during an internal evaluation which prompts models to pursue advanced exploitation using complex attack paths, in an effort to quantify their cyber capabilities.
That's directly from OpenAI.
I will also point out, as I have in other similar press releases, OpenAI have a financial interest in making their AI models sound the most advanced. I remember years back when they refused to release GPT3 because it was too dangerous for mankind... |
Used to be a good one where you could ask the model whether you should drive or walk to the car wash that was 100m away to get your car cleaned. After a lot reasoning, many of the models would tell you to walk to the car wash to which you then had to point out that if you did that you wouldn't actually have a car with you to wash.
Things have moved on a lot but was still quite amusing.
I do tend to use Opus quite a bit nowadays, which is good when suitably marshalled.
SB [Post edited 22 Jul 22:11]
|  |
| Avatar - M101 - Pinwheel Galaxy |
| |
| This is truly extraordinary on 22:01 - Jul 22 with 237 views | StokieBlue |
| This is truly extraordinary on 21:44 - Jul 22 by DanTheMan |
Musk says a lot of utter nonsense. |
Does he say anything but utter nonsense?
SB | |
| Avatar - M101 - Pinwheel Galaxy |
| |
| This is truly extraordinary on 23:36 - Jul 22 with 160 views | armchaircritic59 |
| This is truly extraordinary on 21:03 - Jul 22 by Nthsuffolkblue |
AI is a very powerful tool that, like any other tool, can be very dangerous in the wrong hands or very useful in the right hands.
Of course there is the risk of the unforeseen which is what people understandably fear.
However, I suspect the worst fears will prove very much unfounded. |
Yep, like a lot of " tools " excellent in the right hands, dodgy or worse in the wrong ones. I'm a big fan of AI, use it lot, including today, for various reasons. I do think however, it might be a good idea if some sort of non suffocating regulation was bought in. |  | | |
| |
By continuing to use the site, you agree to our use of cookies and to abide by our Terms and Conditions.
