- Joined
- Jun 12, 2018
- Messages
- 1,495
Computer systems have been defining truth, actually true and false, for some time. The basic model is that inputs are represented as individual values. Each of those values is then weighted and the result aggregated. Then cut off criteria are used to segment the final value into areas of true and false with an indeterminate range between the two.
A computer system will not go into an endless loop; it will provide an answer. The validity of the answer may be problematic, though.
Sometimes it will take 7,500,000 years to come to a conclusion. And sometimes that conclusion is 42.
Best to ask the right question.
The result is dependent upon the training data given to the AI. If it is trained on an equal number of white swans and black swans, the answer to the query, "What color are swans?" would likely be black or white. If the training data is heavily biased towards one color or the other, then the answer will be skewed to the more prevalent training data. It is highly unlikely that the system would come up with gray as an answer. However, this query is not one that I would consider true or false.Not exactly what I was thinking of but I have been struggling to think of an example to illustrate what I meant. Let's imagine two groups of humans living before 1697 when the Dutch explorer Willem de Vlamingh visited Australia. One group of humans in Europe think that all Swans are white. One group of humans in Australia think that all Swans are black. Both adamantly think what they believe is true, and since they have no contact with each other and have never seen the other type of Swan, they are both correct. Yet only one answer can be true, so one must be false.
How would a current "AI" determine what is the truth here?
If values are weighted and then the results aggregated then this would favour the largest group rather than the correct answer. So, would it decide that as their are more people living in Europe that all Swans are white, or would it instead decide that Swans are a pale shade of grey? Neither of those answers is the truth. Both are wrong.
Could it come to the real answer that Swans can be white and also can be black? Or, could it say that it doesn't know the answer?
And that is a relatively straightforward problem that only has two answers. When you instead ask it what the height of a Double Decker Bus is and there are hundreds of different kinds, different ways to measure, errors made in measurements...
orry, but the recent IT 'outage' had nothing to do with Microsoft and the windows 3.1 stuff is apocryphal rumour spread from one report describing their systems as looking like they were designed on Windows 95. The problem was not with the operating system it was in an update from a company called CROWDSTRIKE (not cloudburst), an antivirus and security software company.
In the crowdstrike outage, or cloudburst, 8.5 million window devices were impacted. Not counting losses microsoft might experience, the loss so far is estimated to 5.4 billion dollars. Malaysia's digital minister called on CrowdStrike and Microsoft to consider compensating affected companies. Its doubtful anything will come of that.
There is something about the colour of banknotes too (Bank of England banknotes anyhow) that the photocopier cannot replicate (or at least that was so up until 10 years ago when there were a lot of fakes in circulation) and the colour was always slightly off. In addition, it can replicate the silver thread but it is only printed of the surface (doesn't run inside) and the watermark comes out much stronger as it is also printed on the surface (rather than only being visible when you hold it up to the light.) Those three things are how you spot a fake one. There is also stuff you can only see with an ultraviolet light, and if there are a lot of fakes, they will often all have the same serial number.your copier is designed to stop you copying banknotes by recognising a pattern added to all notes.
This is fine if you have a good idea of what the notes should look like and this is why shops in England get so touchy about accepting notes from Scotland and Northern Ireland*. They simply wouldn't know how to distinguish a fake one from a real. Not a big deal for big department stores and supermarkets but a single fake £20 note taken in a small corner shop represents a significant amount of the day's profit; ie their personal income.There is something about the colour of banknotes too (Bank of England banknotes anyhow) that the photocopier cannot replicate (or at least that was so up until 10 years ago when there were a lot of fakes in circulation) and the colour was always slightly off. In addition, it can replicate the silver thread but it is only printed of the surface (doesn't run inside) and the watermark comes out much stronger as it is also printed on the surface (rather than only being visible when you hold it up to the light.) Those three things are how you spot a fake one. There is also stuff you can only see with an ultraviolet light, and if there are a lot of fakes, they will often all have the same serial number.