I don't know how people use ChatGPT at all. It confidently hallucinated answers to 4 out of 5 my latest "real" questions, with code examples and everything. Fortunately with code I could easily verify the provided solutions are worthless. Granted I was asking questions about my niche that were hard enough I couldn't easily Google them or find a solution myself, but I think that's the bar for being useful. The only thing it got right was finding a marketing slogan.
I've done this and, from what I can tell, it is reasonably accurate. However, I did have an instance where I was asking it a series of questions about the First Peloponnesian War, and partway through our discussion it switched topics to the first part of the Peloponnesian War, which are different conflicts. At least, I think they are. It was quite confusing.
Nero was a Roman Emperor from 54 to 68 AD, known for his controversial and extravagant reign. He was the last emperor of the Julio-Claudian dynasty. Here are some key points about his life and rule:
1. *Early Life and Ascension*: Nero was born Lucius Domitius Ahenobarbus in 37 AD. He was adopted by his great-uncle, Emperor Claudius, becoming Nero Claudius Caesar Drusus Germanicus. He ascended to the throne at the age of 17, after Claudius' death, which many historians believe Nero's mother, Agrippina the Younger, may have orchestrated.
2. *Reign*: Nero's early reign was marked by influence from his mother, tutors, and advisors, notably the philosopher Seneca and the Praetorian Prefect Burrus. During this period, he was seen as a competent ruler, initiating public works and negotiating peace with Parthia.
3. *Infamous Acts*: As Nero's reign progressed, he became known for his self-indulgence, cruelty, and erratic behavior. He is infamously associated with the Great Fire of Rome in 64 AD. While it's a myth that he "fiddled while Rome burned" (the fiddle didn't exist then), he did use the disaster to rebuild parts of the city according to his own designs and erected the opulent Domus Aurea (Golden House).
4. *Persecution of Christians*: Nero is often noted for his brutal persecution of Christians, whom he blamed for the Great Fire. This marked one of the first major Roman persecutions of Christians.
5. *Downfall and Death*: Nero's reign faced several revolts and uprisings. In 68 AD, after losing the support of the Senate and the military, he was declared a public enemy. Facing execution, he committed suicide, reportedly uttering, "What an artist dies in me!"
6. *Legacy*: Nero's reign is often characterized by tyranny, extravagance, and debauchery in historical and cultural depictions. However, some historians suggest that his negative portrayal was partly due to political propaganda by his successors.
His death led to a brief period of civil war, known as the Year of the Four Emperors, before the establishment of the Flavian dynasty.
I also did a brief fact check of a few details here and they were all correct. Zero hallucinations.
Does this make sense? Notice how little it matters if my understanding of Nero is complete or entirely accurate; I’m getting a general gist of the topic, and it seems like a good time.
This is missing the broad concern with hallucination: You are putting your trust in something that delivers all results confidently, even if they were predicted incorrectly. Your counter-argument is lack of trust in other sources (podcasts, the education system), however humans, when they don't know something, generally say they don't know something, whereas LLMs will confidently output incorrect information. Knowing nothing about a certain subject, and (for the sake of argument) lacking research access, I would much rather trust a podcast specializing in a certain area than asking a LLM.
Put more simply: I would rather have no information than incorrect information.
I work in a field of tech history that is under-represented on wikipedia, but represented well in other areas on the internet and the web. It is incredibly easy to get chatGPT to hallucinate information and give incorrect answers when asking very basic questions about this field, whereas this field is talked about and covered quite accurately from the early days of usenet all the way up to modern social media. Until the quality of training data can be improved, I can never use chatgpt for anything relating to this field, as I cannot trust its output.
I am continually surprised by how many people struggle to operate in uncertainty; I am further surprised by how many people seem to delude themselves into thinking that… podcasts… can provide a level of certainty that an LLM cannot.
In life, you exceptionally rarely have “enough” information to make a decision at the critical moment. You would rather know nothing than know some things? That’s not how the world works, not how discovery works, and not even how knowledge works. The things you think are certain are a lot less so than you apparently believe.
It may matter little to you that your understanding is not complete or entirely accurate, but some of my worst experiences have been discussing topics with people who think they have anything insightful to add because they read a wikipedia page or listened to a single podcast episode and then decided that gave them a worthwhile understanding of something that often instead takes years to fully appreciate. A little knowledge and all of that. For one, you don't know what you're missing by omission.
>You call a number and a cab turns up and you pay by the meter or an agreed upon price. How did it work then?
Badly. I was scammed multiple times in different countries (I travel a lot), including my own. And there's a lot of uncertainty and stress involved (no guarantee you share a language with your driver, in case they need to ask any questions). And I hate talking over the phone.
As long as that's an option I'm staying with Uber.
Yes, let's give corporations more power. Image bubble colour indicate the protocol you're using, and nothing more. It don't - and can't - guarantee security (many people learned this lesson with https).
But sure, let's let corporations super-copyright the colour green.
I would call most intelligent space aliens from movies "deeply human". Which makes sense, they were created by humans to tell stories to other humans. So I guess being human is not a prerequisite to being "deeply human". I wonder if real space aliens, if they exist, are in fact like this. The closest earthly thing we have to intelligent aliens - octopi - are not.
I wanted to say that this "obviously" means "5 hours median" i.e. 50%, but I just realised my managers and clients would almost always understand this as "I swear on everything I hold dear this will take 5 hours and not a single minute more" (which is why I avoid sharing my estimates publicly). Funny how it works. Great observation, thanks.
Literal wishful thinking ("powerful technology is always good") and vested interests ("I like building on top of this powerful technology"), same as always.
So all the programmers who work there should live on thin air? I agree that ideally the management should not be there for profit, but come on, the salaries are not even that crazy. I suspect FAANG key employees in that area easily earn multiples of that.
That line of thought is exactly why FAAMG companies tried to lower salaries for CoL when they opened up to more remote roles. I don't know if thst was fair, but it wasn't something appreciated by many engineers during the pandemic.
It's also how and why long ago they tried to outsource a lot of engineering. They still do try. But that's not an easy transition either.
What is the problem of managers of a non-profit company earning around 700k/year and the company is writing blog posts complaining that the the company operation is too expensive? I think if you read it aloud, you will understand it.
When the numbers total $50m in operations and the CEO is making about as much as a principal Google engineer: no, I don't see the issue. Even if he made $0 the issue remains given that every part of the server operation costs more than him.
But sure. What do you think is a fair salary or totalccomp for a founder and CEO of a popular, privacy focused app?
> CEO is making about as much as a principal Google engineer
From a company living from donations... It is illusion (probably a California thing), to think that you are going to compete salary wise with FAANG. The time will tell (well their complaining about money, is already hinting it)...
But they aren't. A principal engineer is not a CEO but probably makes more at top companies.
I don't even work at a FAANG and I was making almost as much as the director there who lists 200k or so total comp. Probably with 20 years less experience to boot. I don't live in SF either; High CoL area but not SF.
That's why I asked you what's a "reasonable" salary. I'm wondering what your POV here is in terms of compensation.
>I think I personally know quite a few people that could do at least as good a job as Signal has at building a messenger app + platform. No offense, but this isn't exactly rocket science.
They are building a secure communicator that a normal person can reasonably use - and succeeding. Something nobody else before them managed to pull off. If this isn't rocket science I don't know what is. Not to mention that they pioneer cryptographic protocols in this area, which other messengers later use.
>This only makes sense if you ignore the world outside the Bay area and assume it's a talentless wasteland.
I'm also from Europe (and love it, despite its flaws) but this comes off like whining. If it's really so easy, maybe the smart people here should create their own Signal and reap that overinflated salaries, what do you think?
Or maybe smart people are not enough and you also need VCs, reasonable taxes, laws... Oh btw, did you hear about those plans of EU to get rid of E2E encryption?
