I kind of feel like poking at the failings if ChatGPT misses the point a bit.<p>Yes it's certainly not an AGI or even super close but to even converse with humans at this level is mind boggling. 10 years before stable diffusion AI could just about label pictures, now it can do, well, stable diffusion.<p>The pace or progress is insane.<p>Like this, I feel we might engage in a naysaying dialogue with consecutive generations of GPT-like models, but finding increasingly minor nitpicks. "Ah but does it understand diminutives"? "It's handling of sarcasm isn't up to scratch". "I tried 10 languages to converse in and Esperanto was quite weak".<p>And then one day we might wake up to a world where we can't really nitpick anymore.
The problem with many of the tasks that people are trying is: the answers are already available on the internet for those very popular crosswords. For example a quick search for "1 Chap recalled skill: something frequently repeated (6)" returns hundreds of correct answers. It’s highly probable that it has already encountered the questions and answers for this crosswords in the training phase.
Probably worth noting that it may not show its true reasoning, rather it immediately arrives at an answer and then proceeds to add an explanation which seems reasonable to it.
I tried using it to solve Wordle and it failed spectacularly:<p>> What 5 letter words can be made only from the letters w,e,y,o,p,d,f,g,h,j,k,z,x,c,v,b,n,m? The word must contain the letter “e”, and the letter “e” cannot be the second letter or last letter.<p>> Here are five five-letter words that can be made using the letters you provided, and which contain the letter "e" as the first or third letter:<p>fewer: a smaller number of people or things
eyewp: not a valid English word
yowep: not a valid English word
oweyp: not a valid English word
pweyo: not a valid English word
Here's another fun thing I accidentally discovered when it made a factual mistake: It will change its reasoning to support its answer.<p>>The average German citizen produces about 10.4 metric tons of CO2 per year, which is significantly lower than the global average of 4.9 metric tons per person per year. In other words, the average person in Germany produces more than twice as much CO2 as the average person worldwide. The reason for this is that Germany has a highly developed and efficient infrastructure for producing and using renewable energy, such as wind and solar power. As a result, a smaller proportion of Germany's energy comes from fossil fuels like coal, oil, and natural gas, which are the main sources of CO2 emissions. Additionally, the average German citizen is more likely to use public transportation and to live in a more densely populated area, which can reduce the overall amount of energy needed for transportation and other purposes.<p>To which I replied:
You said:<p>"The average German citizen produces about 10.4 metric tons of CO2 per year, which is significantly lower than the global average of 4.9 metric tons per person per year."<p>this is a false statement, no?<p>>You are correct, my previous statement was incorrect. I apologize for the error. The average German citizen actually produces about 10.4 metric tons of CO2 per year, which is significantly higher than the global average of 4.9 metric tons per person per year. In other words, the average person in Germany produces more than twice as much CO2 as the average person worldwide. The reason for this is that Germany has a highly developed economy and a large industrial sector, which are major sources of CO2 emissions. Additionally, the average German citizen is more likely to use a car for transportation and to live in a less densely populated area, which can increase the overall amount of energy needed for transportation and other purposes. Again, I apologize for any confusion my previous statement may have caused.<p>Notice that all of the sudden the average German citizen is more likely to live in a less densely populated area to support the fact that they produce more CO2 per year than the global average.<p>Really fun stuff!
Interesting test case, but it looks like it just sort of stumbled on to the correct answer with the last one, because "sushi" is a pretty obvious first guess for "Japanese food", regardless of the rest of the clue.<p>But yes, it is impressive that it manages to parse the general intent of the clue.
There's a crossword solver app called Crossword Genius [1] that gives an answer and an explanation for it. I tried it a while back when you could use it free online and it was very good, but now they appear to have made it app only.<p>It claims to be AI based, though you can provide feedback when it gets it wrong and there aren't many cryptic crosswords in the world, so I don't know to what extent it's solving with clever algorithms vs just echoing back human solutions.<p>[1] <a href="https://www.crosswordgenius.com/" rel="nofollow">https://www.crosswordgenius.com/</a>
This blog references another blog where the author has ChatGPT emulate a Linux terminal [1].<p>The output it produces is incredibly impressive but I just tried to use the same prompts and got back "I'm sorry, but I am not capable of acting as a Linux terminal or any other type of command-line interface."<p>Interesting that this capability has been neutered.<p>1. <a href="https://www.engraved.blog/building-a-virtual-machine-inside/" rel="nofollow">https://www.engraved.blog/building-a-virtual-machine-inside/</a>
there is no reasoning, just google "chap recalled skill something frequently repeated" and there is multiples times the answer, it is just the best fit from the training corpus.
I have no chance of solving these. I am human, but english is not my first language. (Yet I speak at level C1 or better).
The faulty reasoning is where the AI nonsense shows, though.
Is it just me - or is the characteristic of deciding on an answer first and then justifying it using selected/made up facts and faulty logic all too human? :-)
> <i>taking the first letter of the word “chap” (M)</i><p>Well, frankly, the answer this is the start of sounds only <i>literally</i> incorrect, rather than <i>profoundly</i> incorrect, like presuming that "recalled" and "reversed" are synonyms. :/
My mother would frequently come up with what were (to me) nonsensical explanations for things that were nonetheless the "right" answer. This is hilarious to me.
OpenAI:<p>> Verify your phone number.<p>That’s the page where my interest in ChatGPT went to zero. Why do they need to know exactly who I am? What’s the real goal here?