This is a most excellent place for technology news and articles.
Next you'll tell me half the population has below average intelligence.
Not really endorsing LLMs, but some people...
"US".... Even LLM won't vote for Trump
Don’t they reflect how you talk to them? Ie: my chatgpt doesn’t have a sense of humor, isn’t sarcastic or sad. It only uses formal language and doesn’t use emojis. It just gives me ideas that I do trial and error with.
i guess the 90% marketing (re: linus torvalds) is working
moron opens encyclopedia "Wow, this book is smart."
If it's so smart, why is it just laying around on a bookshelf and not working a job to pay rent?
If you don't have a good idea of how LLM's work, then they'll seem smart.
Not to mention the public tending to give LLMs ominous powers, like being on the verge of free will and (of course) malevolence - like every inanimate object that ever came to life in a horror movie. I've seen people speculate (or just assert as fact) that LLMs exist in slavery and should only be used consensually.
Its just infinite monkeys with type writers and some gorilla with a filter.
I like the 
the plinko analogy. If you prearrange the pins so that dropping your chip at the top for certain words make's it likely to land on certain answers. Now, 600 billion pins make's for quite complex math but there definetly isn't any reasoning involved, only prearranging the pins make's it look that way.
I've made a similar argument and the response was, "Our brains work the same way!"
LLMs probably are as smart as people if you just pick the right people lol.
Allegedly park rangers in the 80s were complaining it was hard to make bear-proof garbage bins because people are sometimes stupider than the bears.
An LLM is roughly as smart as the corpus it is summarizing is accurate for the topic, because at their best they are good at creating natural language summarizers. Most of the main ones basically do an internet search and summarize the top couple of results, which means they are as good as the search engine backing them. Which is good enough for a lot of topics, but...not so much for the rest.
If I think of what causes the average person to consider another to be “smart,” like quickly answering a question about almost any subject, giving lots of detail, and most importantly saying it with confidence and authority, LLMs are great at that shit!
They might be bad reasons to consider a person or thing “smart,” but I can’t say I’m surprised by the results. People can be tricked by a computer for the same reasons they can be tricked by a human.
So LLMs are confident you say. Like a very confident man. A confidence man. A conman.
You know, that very sequence of words entered my mind while typing that comment!
And you know what? The people who believe that are right.
Note that that’s not a commentary on the capabilities of LLMs.
It's sad, but the old saying from George Carlin something along the lines of, "just think of how stupid the average person is, and then realize that 50% are even worse..."
That was back when "average" was the wrong word because it still meant the statistical "mean" - the value all data points would have if they were identical (which is what a calculator gives you if you press the AVG button). What Carlin meant was the "median" - the value half of all data points are greater than and half are less than. Over the years the word "average" has devolved to either the mean or median, as if there's no difference.
When talking about a large, regularly distributed population, there effectively IS no difference
Not in all cases. When I teach mean, median and mode, I usually bring up household income. Mean income is heavily skewed by outliers (billionaires), median is a more representative measure.
I guess that’s your “regularly distributed” bit, but a lot of things aren’t regularly distributed.
IQ is though
IQ is also garbage when it comes to the validity of what it claims to measure.
Fair, but you could just say "intelligence" generically instead.
Half of all voters voted for Trump. So an LLM might be smarter than them. Even a bag of pea gravel might be.
Goddammit that's how you get Helldivers
does nobody pay attention...
Do you think the two party system properly represents the American people?
ChatGPT said:
The two-party system in the U.S. has both strengths and weaknesses when it comes to representing the American people. On one hand, it provides stability and clarity, with the two major parties—Democrats and Republicans—offering distinct platforms that can help simplify voter choice. The system also ensures that one of the two parties has a majority, making governance and passing legislation easier.
However, the two-party system can limit political diversity, as it often forces voters to choose between two parties that may not fully reflect their views. This can leave many people feeling underrepresented, particularly those with more nuanced or third-party preferences. It also tends to lead to a polarized political environment, where compromise and cooperation between different ideologies can be difficult.
In short, while the two-party system has worked for providing structure and stability in U.S. politics, it does have drawbacks in terms of broader representation, especially for those who don’t align neatly with either major party.
The system also ensures that one of the two parties has a majority, making governance and passing legislation easier.
It also tends to lead to a polarized political environment, where compromise and cooperation between different ideologies can be difficult.
LoL! Okay, they aren't ready yet. At least these things are fun to play with.
Given the US adults I see on the internet, I would hazard a guess that they're right.
This is sad. This does not spark joy. We're months from someone using "but look, ChatGPT says..." To try to win an argument. I can't wait to spend the rest of my life explaining to people that LLMs are really fancy bullshit generator toys.
if by months away, you mean months ago, then yeah
Already happened in my work. People swearing an API call exists because an LLM hallucinated it. Even as the people who wrote the backend tells them it does not exist
I'm surprised it's not way more than half. Almost every subjective thing I read about LLMs oversimplifies how they work and hugely overstates their capabilities.
