How do you navigate this blog to read the other articles? I couldn't find any way to read the one on gpt4 (clicking the underlined "wrote about" does nothing) and twofergoofer.com/blog goes to a 404.
Bard is much worse at puzzle solving than ChatGPT
11–20 of 86 posts
Re: Bard is much worse at puzzle solving than ChatGPT
#12That's a clever game to get it to play. Today I asked ChatGPT to give me 1000 Fibonacci numbers starting with the 2000th number and it crashed. Later I asked it the same prompt and it repeatedly gave me code to calculate the Fibonacci numbers in Python.
> and it crashed
I hope you understand that it's only because of inability of OpenAI's servers to keep up with demand or some issue in their backend code - language models themselves can't "crash" like normal programs on some kind of input, because they "just" generate new tokens.
Re: Bard is much worse at puzzle solving than ChatGPT
#13Earlier quoted context omitted.
s/Microsoft/Google/ http://www.paulgraham.com/microsoft.html
But was Microsoft ever cool in the sense that Google was circa 2005? (Asking honestly, I'm too young to remember that period.)
No, not really. They were seen as a serious business used by other serious businesses. IMO google pioneered the "cool tech company" with their 20% time, "don't be evil", unique campus life, etc.
Re: Bard is much worse at puzzle solving than ChatGPT
#14Earlier quoted context omitted.
s/Microsoft/Google/ http://www.paulgraham.com/microsoft.html
But was Microsoft ever cool in the sense that Google was circa 2005? (Asking honestly, I'm too young to remember that period.)
No. I'm an old-timer, and there has not been one picosecond since the moment of its founding when Microsoft was cool.
Re: Bard is much worse at puzzle solving than ChatGPT
#15"Bard is much worse than ChatGPT at solving an obscure word game I invented" would have been a more honest title, but would probably generate less clicks for the author.
Bard may still be much worse than ChatGPT at solving all kinds of puzzles, but the article is click bait for promoting the author's word game, not an actual investigation that warrants that conclusion.
Re: Bard is much worse at puzzle solving than ChatGPT
#16Earlier quoted context omitted.
But was Microsoft ever cool in the sense that Google was circa 2005? (Asking honestly, I'm too young to remember that period.)
No. I'm an old-timer, and there has not been one picosecond since the moment of its founding when Microsoft was cool.
Flight Simulator 1995
Re: Bard is much worse at puzzle solving than ChatGPT
#17How do you navigate this blog to read the other articles? I couldn't find any way to read the one on gpt4 (clicking the underlined "wrote about" does nothing) and twofergoofer.com/blog goes to a 404.
I was curious to read it, too, so I googled to find the article.
It's located at https://twofergoofer.com/blog/gpt-4
Re: Bard is much worse at puzzle solving than ChatGPT
#18"Bard is much worse than ChatGPT at solving an obscure word game I invented" would have been a more honest title, but would probably generate less clicks for the author. Bard may still be much worse than ChatGPT at solving all kinds of puzzles, but the article is click bait for promoting the author's word game, not an actual investigation that warrants that conclusion.
what's wrong with that?
the use of novel puzzles is frankly awesome because there's a much lower chance of contamination from previous puzzles so we get a chance to see how much generalization they've achieved.
Re: Bard is much worse at puzzle solving than ChatGPT
#19That's a clever game to get it to play. Today I asked ChatGPT to give me 1000 Fibonacci numbers starting with the 2000th number and it crashed. Later I asked it the same prompt and it repeatedly gave me code to calculate the Fibonacci numbers in Python.
> and it crashed I hope you understand that it's only because of inability of OpenAI's servers to keep up with demand or some issue in their backend code - language models themselves can't "crash" like normal programs on some kind of input, because they "just" generate new tokens.
I know little more than what I've read about LLMs and other models. I just got it to do them again and it output them rather quickly: https://imgur.com/a/jfviCCe
Re: Bard is much worse at puzzle solving than ChatGPT
#20"Bard is much worse than ChatGPT at solving an obscure word game I invented" would have been a more honest title, but would probably generate less clicks for the author. Bard may still be much worse than ChatGPT at solving all kinds of puzzles, but the article is click bait for promoting the author's word game, not an actual investigation that warrants that conclusion.
what's wrong with that? the use of novel puzzles is frankly awesome because there's a much lower chance of contamination from previous puzzles so we get a chance to see how much generalization they've achieved.
I'm complaining about the title writing a check that the blog post can't cash.