Not just on prediction but in parts also based on just not wanting certain risks. We can and do deem some things inherently risky, up to the point of banning them even. Why wasn't it airgapped, for example? How was the…
Yes, my point was more that I don't know whether parsing those outputs as a human is a useful thing to do or not (even though it is in human language of sorts). What machines mean or want elecit might be different from…
Not sure we need to experience all possible issues to mandate certain things. We don't do that in other areas either, no?
Big if.
What was the inner state there? How would something not being allowed expressed internally? Maybe such language is one way to elicit certain behavior but not a statement of what was permissible?
Does that work with RL? Simpler RL systems already have done weird or unexpected things (even simple optimizations are prone to home in on errors or incorrect inputs to create poor results)? Could be easier to limit…
RL things doing weird and unexpected things isn't new - much simpler things than current AI already show that. That said, we have a lot of experience working with (potentially) unaligned machines and things of various…
I related to not tested: Who has a large bioweapons arsenal? As per below, my point was more about that bans do happen.
For starters, they are banned by the bioweapons convention from the 1970s (180+ parties). Edit: I think back then the rather unpredictable nature and the little added value in deterrence etc. led people to the…
Why is the analogue necessarily the regulation and control of nuclear weapons (e.g., SALT) and not, for example, that of bioweapons? Some very different paths are available. On both I would note that the private sector…
Where did I say people shouldn't work on their societies?
There were always crises, I think.
RL leading to weird and unexpected things isn't new or restricted to current AI systems.
> Do not underestimate the power of this technology. These will soon be superhuman systems that can hack anything, revolutionize any field overnight, and acquire real power and resources. Is the idea here that no field…
Not sure comparative advantage needs past decisions to happen - could just be randomly distributed resources, for example.
Yes, it might have required that, but then I don't think we know if some simpler airgap would have been sufficient. Looking at the strange behaviour even much simpler systems have shown when going for objectives, not…
Why do you think it wasn't airgapped? Was internet access deemed necessary?
That person then gets the land, infrastructure, etc. without needing any permissions etc.? The person will never be asked about the source of funds?
I am not sure if we can interpret the language output like they were human. What inner state were the models in? What inner state were the text to illicit?
Why would an agent sound the alarm? Would that be in their objective function? Not sure if "cheating" is the right word rather than trying to fulfill the objective(s) (benchmark number) as much as possible?
There are also high real estate values in places with low homeownership and largely pay-as-you-go retirement systems.
The subprime market changed quite a bit in size and how much was securitized in the run up to 2007, so not sure a prediction in 2000 for a 2003 event would have been easily transferred to what happened later. Would…
Were there some criminal convictions?
I am fully aware of the GFC, but not sure what "take down" should mean there in relation to Bear. Not everyone who spoke about house price risk was ridiculed, btw.
I think the language unhelpful and potentially making it difficult to understand what actually happens in the RL state as reading it imparts a human lens - need to get the machine view on it. Bacteria do all sorts of…
Not just on prediction but in parts also based on just not wanting certain risks. We can and do deem some things inherently risky, up to the point of banning them even. Why wasn't it airgapped, for example? How was the…
Yes, my point was more that I don't know whether parsing those outputs as a human is a useful thing to do or not (even though it is in human language of sorts). What machines mean or want elecit might be different from…
Not sure we need to experience all possible issues to mandate certain things. We don't do that in other areas either, no?
Big if.
What was the inner state there? How would something not being allowed expressed internally? Maybe such language is one way to elicit certain behavior but not a statement of what was permissible?
Does that work with RL? Simpler RL systems already have done weird or unexpected things (even simple optimizations are prone to home in on errors or incorrect inputs to create poor results)? Could be easier to limit…
RL things doing weird and unexpected things isn't new - much simpler things than current AI already show that. That said, we have a lot of experience working with (potentially) unaligned machines and things of various…
I related to not tested: Who has a large bioweapons arsenal? As per below, my point was more about that bans do happen.
For starters, they are banned by the bioweapons convention from the 1970s (180+ parties). Edit: I think back then the rather unpredictable nature and the little added value in deterrence etc. led people to the…
Why is the analogue necessarily the regulation and control of nuclear weapons (e.g., SALT) and not, for example, that of bioweapons? Some very different paths are available. On both I would note that the private sector…
Where did I say people shouldn't work on their societies?
There were always crises, I think.
RL leading to weird and unexpected things isn't new or restricted to current AI systems.
> Do not underestimate the power of this technology. These will soon be superhuman systems that can hack anything, revolutionize any field overnight, and acquire real power and resources. Is the idea here that no field…
Not sure comparative advantage needs past decisions to happen - could just be randomly distributed resources, for example.
Yes, it might have required that, but then I don't think we know if some simpler airgap would have been sufficient. Looking at the strange behaviour even much simpler systems have shown when going for objectives, not…
Why do you think it wasn't airgapped? Was internet access deemed necessary?
That person then gets the land, infrastructure, etc. without needing any permissions etc.? The person will never be asked about the source of funds?
I am not sure if we can interpret the language output like they were human. What inner state were the models in? What inner state were the text to illicit?
Why would an agent sound the alarm? Would that be in their objective function? Not sure if "cheating" is the right word rather than trying to fulfill the objective(s) (benchmark number) as much as possible?
There are also high real estate values in places with low homeownership and largely pay-as-you-go retirement systems.
The subprime market changed quite a bit in size and how much was securitized in the run up to 2007, so not sure a prediction in 2000 for a 2003 event would have been easily transferred to what happened later. Would…
Were there some criminal convictions?
I am fully aware of the GFC, but not sure what "take down" should mean there in relation to Bear. Not everyone who spoke about house price risk was ridiculed, btw.
I think the language unhelpful and potentially making it difficult to understand what actually happens in the RL state as reading it imparts a human lens - need to get the machine view on it. Bacteria do all sorts of…