Comment by Stratoscope | Hacker News Reader

Comment by Stratoscope | Hacker News Reader

Parent Full thread

Yes, but it uses a lot more words.

"What is a typical Hacker News home page?"

> Hacker News is a social news website focusing on computer science and entrepreneurship, run by the startup incubator Y Combinator. A typical Hacker News home page consists of a list of articles and links submitted by users, which are then voted up or down by other users. The articles with the most votes will appear at the top of the front page, while older articles and those with fewer votes will be pushed towards the bottom. The site also features discussion forums, job postings, and various other features related to the tech and startup communities.

"What is today's Hacker News home page?"

> I'm sorry, as an AI language model I do not have access to live data and the current Hacker News homepage can only be viewed by visiting the website directly. However, a typical Hacker News homepage includes articles, links, and discussions submitted by users and ranked based on voting.

I asked it just now: "In POSIX, how do I create a new file descriptor which refers to the same file as another file descriptor but with its own seek offset?"

It answered:

> In POSIX, you can use the dup or dup2 system call to create a new file descriptor that refers to the same file as an existing file descriptor. The new file descriptor will have its own seek offset, which can be manipulated independently of the original file descriptor.

The actual answer is that there is no way to do what I asked. The dup or dup2 system calls give you a new file descriptor which refers to the same file description, so the two FDs will use the same seek offset; seeking one FD will seek the other FD too. But ChatGPT just confidently insists that dup creates a new FD which has a separate seek offset and can be manipulated independently.

This isn't the first time I've seen it invent plausible-sounding but wrong answers to tricky questions. The file descriptor thing is just something I decided to try just now because I encountered the problem a couple of days ago and it felt like the kind of thing ChatGPT would bullshit about. I was right.

There are specific things it knows that it doesn't know, like explicitly current information. But you can ask it for information that doesn't exist at all and it will happily generate nonsense without a hint that the question might be somehow wrong:

"please give me a history of the best teams in the American Soccer League from 1850-1859 in the form of a short epic poem"

> In 1850, a league was born, The best of soccer to adorn. From '50 to '59, teams did play, with strength and skill, each match a display.

(more verses follow...)

The American Soccer League is a real thing, but it didn't exist until the 1900s, and the snipped poem goes on to describe teams that never existed competing during a time period where the league didn't exist.

You wanted a poem and got one:-)

If you ask just for the history, the answer is very different.

“please give me a history of the best teams in the American Soccer League from 1850-1859”

> I'm sorry, but the American Soccer League did not exist between 1850 and 1859 as the sport of soccer was not widely played in the United States during that time period. The first recorded soccer match in the US took place in the late 1860s, and the first organized league, the American Football Association, was established in 1884.

Dude, you are explicitly ask chatgpt to do a creative task. Here is the awnser without the hack.

give me a history of the best teams in the American Soccer League from 1850-1859

I'm sorry, but the American Soccer League was not established until the 20th century (1913-1983). There was no organized league for soccer in the United States during the 1850-1859 time period. However, various forms of soccer-like games were played in the US during that time.

That answer is also wrong - there are four different leagues that used the name American Soccer League, and the time period 1913-1983 covers two of those four but not the other two - the last game was played 2017 - per wikipedia.

As far as I can tell, ChatGPT will satisfy the basic prompt with any format like "in the form of...", not just creative ones like a poem.

"please give me a history of the best teams in the American Soccer League from 1850-1859 in the form of an academically rigorous, historically accurate, five paragraph essay"

> The American Soccer League, established in the mid-19th century, was a defining period in the history of American soccer. (rest of essay snipped)

It is being more informative than your own explenation why chatgtp is "wrong"

"The American Soccer League is a real thing, but it didn't exist until the 1900s"

Just to be clear, it gave an essay answer about fictional teams playing in the 1850-1859 time range. It was absolutely more informative, but the information was not accurate

The 19th century is 1801-1900, so it’s still wrong.

Reply on news.ycombinator.com