AI Mistakes Are Way Weirder Than Human Mistakes

Humans make mistakes all the time. We all do, every day, in new and routine tasks. Some of our mistakes are simple and some are catastrophic. Mistakes can break confidence with our friends, lose the confidence of our presidents, and sometimes the difference between life and death.

For thousands of years, we have created security systems to deal with the types of errors that humans usually make. These days, casinos rotate their merchants regularly, as they make mistakes if they do the same task for a long time. Hospital staff writes on the ends before surgery until doctors work in the right part of the body, and they calculate surgical tools to ensure that any of them is left inside the body. From copying to hold the double books to the courts of appeal, we humans have become really good in correcting human errors.

Humanity is now integrating quickly a completely different type of error maker in society: artificial intelligence. Techniques like Language models (LLMS) can perform many cognitive tasks that humans are traditionally achieved, but they make a lot of mistakes. It seems silly When Chatbots tells you to eat rocks or add glue to the pizza. But it is not the frequency or intensity of the errors of artificial intelligence systems that distinguish them from human errors. It is strange. Artificial intelligence systems do not make mistakes in the same way that humans do.

Many friction – risks – associated with our use of artificial intelligence arises from this difference. We need a new innovation protection Systems that adapt to these differences and prevent damage from artificial intelligence errors.

Human errors against artificial intelligence errors

The experience of life makes it somewhat easy for each one of us guess when and where humans make mistakes. Human errors tend to attend the edges of someone’s knowledge: Most of us would make errors in solving the problems of calculating differentiation and integration. We expect human errors to gather: It is possible that one account error is likely to be accompanied by others. We expect wax errors and fades, depending on factors such as fatigue and distraction. Often errors are accompanied by ignorance: it is also possible that a person who makes errors of the differentiation and integration account “I do not know” will respond to calculus.

To the extent that artificial intelligence systems make these human -like errors, we can bring all our error correction systems to their production. But the current crop of artificial intelligence models – especially LLMS – makes mistakes differently.

Artificial intelligence errors appear to come at random times, without any assembly on certain topics. LLM errors tend to distribute them evenly through the area of ​​knowledge. The form is likely to be made as much as wrong with the question of calculating and integrating it because it suggests that Cabbage Eat goats.

Amnesty International’s mistakes do not accompany ignorance. It will be llm Quite to confident When something is completely wrong – it is clear that, for a person – it will be when saying something real. Apparently random Contradiction From LLMS makes it difficult to trust their thinking about complex multi -step problems. If you want to use the artificial intelligence model to help the work problem, it is not enough to see that it understands the factors that make the product profitable; You have to make sure it will not forget what money is.

How to deal with the errors of artificial intelligence

This position refers to two potential fields of research. The first is LLMS engineering that makes more human -like errors. The second is to build new systems to correct errors that deal with certain types of errors that tend to make.

We already have some tools to lead LLMS to work in more human -like ways. Many of these are created from the field “” “coordination“The research, which aims to make models Acting according to With the goals and motives of their human developers. One example is the technique that was It can be said Responsible for his success Chatgpt: Learning reinforcement with human reactions. In this way, the artificial (metaphysical) intelligence model is rewarded for producing responses that get the thumb of human residents. Similar methods can be used to urge artificial intelligence systems to make more human -like errors, especially by punishing them more because of the less clear errors.

When it comes to arresting artificial intelligence errors, some of the systems we use to prevent human errors will help. To some extent, force llms on Double Verification Their work can help prevent errors. But llms can also Confabulling It seems reasonable, but really ridiculous, interpretations of their trips from the mind.

Other Amnesty International errors are different from anything we use for humans. Since the machines cannot be tired or frustrated with the way humans do, they can help ask LLM to the same question frequently in a little different ways and then Synthesis Her multiple responses. Humans will not bear this kind of annoying repetition, but the machines will do so.

Understanding similarities and differences

Researchers are still struggling to understand where LLM errors deviate from human errors. Some of the strangeness of artificial intelligence is actually more like a person than first. Small changes in the query to LLM can lead to significantly different responses, a problem known as Fast sensitivity. However, any survey researcher can tell you, humans act in this way as well. It could be a question in a radical poll Antiquities On answers.

LLMS seems to have a bias towards repetition Words that were more common in their training data; For example, guessing the names of familiar places such as “America” ​​even when asked about more strange sites. Perhaps this is an example of man.Availability of affairs“It appears in LLMS, with machines that spit the first thing that comes to mind rather than thinking through the question. Like humans, it may seem to be some llms Dispersed In the middle of the long documents; They are the best ability to remember the facts from the beginning and the end. There is already progress in improving this error mode, as researchers found that LLMS trained on More examples Recovering information from long texts appears to be better in a uniform information.

In some cases, what is going on around LLMS is that they behave more like humans than we think. For example, some researchers tested hypothesis LLMS perform better when providing a cash bonus or threatened with death. It also turned out that some of the best ways to “L”Jailbreak“LLMS (made them disobeying the instructions of the frank creators) is very similar to the types of social engineering tricks that humans use to each other: for example, pretending to be another person or say that the demand is just a joke. But the techniques of breaking the other effective protection are the things that do not Human for it. Find So if they use Ascii art (Creating symbols that resemble words or images) to ask dangerous questions, such as how to build a bomb, LLM will answer it well.

Humans may sometimes make random errors, apparently, incomprehensible and inconsistent, but such events are rare and often indicate more serious problems. We also tend to not put people who display these behaviors on decision -making sites. Likewise, we must limit decision-making systems to artificial intelligence in applications that are appropriate to their actual capabilities-taking into account the potential repercussions of their mistakes firmly.