nicksrose7224

What is the accuracy of this method vs manual entry?

They do this already, but the problem is it takes me more time to verify if what they're saying is correct than to just use a search engine. All the LLMs constantly make stuff up & have extremely low precision & recall of information

disagree - i actually think all the problems the author lays out about Deep Research apply just as well to GPT4o / o3-mini-whatever. These things just are absolutely terrible at precision & recall of information

I don't think this is a good take. Discovery & science are inherently meaningful even if the applications are not immediately felt. Nuclear magnetic resonance (NMR) was discovered in 1938, but there was no obvious applicability of it to everyday life. In 1971, 33 years later, Paul Lauterbur used it to develop the first MRI

super bad take. by this logic nobody should be excited about any technology whatsoever

tbh i could not tell the difference between this & generic technostep made by people. Sounds just as crappy to me

I dont think they're saying its up to tech companies to decide what has value, more that the development of new technology itself ends up deciding for the rest of the world how things are valued.

It's been this way for 10,000 years since the invention of the wheel. New inventions change how things are valued by making it easier for people do more work with less time.

This sounds compelling but where i always get stuck is on trust of what the LLM / agent spits back out. Every time I've tried to use it for one of the above use cases you mentioned and then actually dug into the sources it may or may not mention, it's almost always highly imprecise, missing really important details, or straight up completely lying or hallucinating.

how do you get around this issue?

Granted on (3), you can just verify yourself by running the code, so trust/accuracy isn't as much an issue here but still annoying when things don't work.

Are you saying it would have been a good thing for your wife's parents not to reproduce? Where would that leave her and you? (noted that childhood you described sounds awful, i agree)

this is not a strong counter argument. Costs will come down. When there is insanely high demand for a product (like there is here) and the thing makes people more productive, costs always come down due to pure incentives to make it cheaper. This happened with electricity, the car, air travel, solar power, etc etc

my suspicion is that FTL travel wouldn't work with this drive because of what the wikipedia article states here:

"Another possible issue is that, although the Alcubierre metric is consistent with Einstein's equations, general relativity does not incorporate quantum mechanics. Some physicists have presented arguments to suggest that a theory of quantum gravity (which would incorporate both theories) would eliminate those solutions in general relativity that allow for backward time travel (see the chronology protection conjecture) and thus make the Alcubierre drive invalid."

My fun layman conjecture based on absolutely no credible knowledge of this area beyond reading articles like this is:

-- the universe has a forward direction of time & causality that is as unbreakable as exiting from a black hole is

-- in a black hole space & time are so warped they sort of switch roles - any direction you try to move in X,Y,Z only brings you closer to the singularity. In much the same way I think the outside universe operates in Time - no matter what you do, you move forward in time.

-- My somewhat unpleasant belief here is the reason you and everything in the universe can only move forward in Time is because of the Block universe[1] concept: all of X,Y,Z,T are already set & predetermined, so it makes no sense to actually try to change your path through it.

-- All of these things put together invalidate the concept of FTL travel, because FTL travel (even with a clever trick like warping spacetime) would violate causality & allow travelers to go back in time

[1] https://en.wikipedia.org/wiki/Eternalism_(philosophy_of_time...

I see this argument all the time. Why are you assuming that this technology just "stops" at the LLM level?

If I'm openAI or Google or whatever, I'm definitely going to run extra classifiers on top of the output of the LLM to determine & improve accuracy of results.

You can layer on all kinds of interesting models to make a thing that's generally useful & also truthful.

That just seems like a rebranding of "the internet" to me

I got tired of spending hours reading through every review across several different Airbnbs when deciding where to stay with friends, especially now with hidden chores & other "gotchas" you can only find by seeing what people wrote about the place in text.

I built this tool powered by GPT4 to grab reviews from each property listing you put in, then use GPT4 API to find the "pros" and "Cons" of each place.

You can also ask any question you want to about the places you've analyzed, including "Is street parking easily available?" and "do you have to do any chores before checking out?"

Hope it's helpful & let me know how to make it more useful!

most (all?) self driving companies are electric. Cruise, Waymo, Tesla

try asking for chocolate chip cookie recipe on chatgpt, it works awesome already. The only issue i see is I can't verify in general if the recipe is accurate (like all things ChatGpt outputs). But these cookies i just happen to know are correct

I think it's more likely they got it wrong and are referring to what they assume the size of the universe is. It's hard to grasp why the observable universe is 92 billion ly in diameter

Without any actual implications of them "taking responsibility" too

he's doing it to pump up his twitter followers, which is why this whole article bugs me. It's a rather transparent attempt to gain followers without adding anything of real value

While i'm on my soapbox, i dont understand this mentality that wealth creation is a positive-sum game. Me buying a property to turn it into an Airbnb that I lease out to generate money directly takes away supply from someone trying to buy a house or a similar asset.

I would love to hear some examples of wealth generation that do not take away opportunity or money directly or indirectly from other people

[edit] below commenters have some great points, i'm reconsidering my stance on this point

This is a pretty lazy and non-value additive article honestly. All it does it just reference things Naval or Warren buffet has said and then “subscribe to my newsletter" at the bottom.

I feel like you could easily write something like this by doing a scrape(Naval's twitter) + scrape(buffet's wiki page) -> GPT3_summarize(that content) and you'd get this article.

Is there any data to back this up? (not attacking, just genuinely curious, i love learning about mass extinctions)

inflation is a giant beast with multiple causes, one of which is definitely stimulus. There are others too, including the cause you listed. Most things have multiple causes

i think this is a bit pessimistic. You can also use GPT-3 or similar technologies to much more easily train a fine-tuned "real vs fake" review classifier with fewer training examples than was previously necessary.

GPT-3 like all tech is double-edged I think. Has good & bad things about it

This is a really nice breakdown -- I made a little side project that falls into your "Extractive" and "Comparisons" bucket: https://www.tripwise.me/

My tools uses GPT-3 to dig through Airbnb reviews to find the "cons" of staying at a particular place and summarize them neatly. You can also ask any question at all in natural language about all the listings you're evaluating.

I'm bookmarking your repo for future reference, this is very useful

I am using it for a little project to make deciding between Airbnbs easier: https://www.tripwise.me/

You basically just enter in the Airbnb URLs you're considering, and it'll use GPT-3 to scrape through the reviews in order to find anything negative or positive people are saying about the listings.

You can also ask any question you want at all, and it'll return answers (if people have mentioned it in their reviews). For example "Is the air conditioning loud?"

I would love to hear what others are using GPT-3 for!