Background: I am personally a long-term value investor (a la Sir Templeton or Buffet †), but annually breakfast with a retired "numbers guy" (who's currently building his short-term trading strategy). For decades he worked finance for among the largest accounting firms in the world...
Since 2016, our mutual friend and I have been adamently suggesting he look into "this bitcoin thing" — his response was typically [disinterested].
At a recent breakfast, it was explained how "talking with ChatGPT finally convinced [him] that you guys have been correct about Bitcoin all along."
When asked "what did ChatGPT explain to you that we two humans could not?!"
His response was simply "I never got embarrassed asking the computer any finance questions, even stupid/simple ones; I've always been the finance guy with answers so I forgot how to be humble in unexplored topics."
Pretty damn humbling, indeed; now if only he had listened back in 2016 =D
> His response was simply "I never got embarrassed asking the computer any finance questions, even stupid/simple ones; I've always been the finance guy with answers so I forgot how to be humble in unexplored topics."
I think I'm the opposite. My feeling is that anything I type into ChatGPT gets stored in a database, ready to be leaked at some future date, or read by prying eyes without my knowledge. I'm more careful about what I type into it than what I say out loud in front of my friends.
Wow! Great disclosure! I find it hard to read though, since the text doesn't properly capitalize the start of sentences. Messes up with the natural language parser I have in my head :)
On my newest Toyota, they finally made it so you cannot disable the seatbelt chime.
As a decades-long seatbelt-FORGETTER (I'm not anti-seatbelt, literally forgot!), not being able to change the vehicle's behavior actually led to a change in mine [I always "buckle up" before even unparking]..!
Time in the markets beats timing the market if you actually have capital to throw around to gleam a decent 5% yearly return. If you don't have much capital, you have to time the market like hell to build up your capital to a level where 5% yoy actually is a decent amount of money.
5% return is a pretty common estimate for passive investing. I certainly didn't come up with it, smarter people than me did and spread it all over financial news media.
Your risk tolerance changes. If you are living on $4000/month and have $500 to invest, you may as well bet those $500 on black. If you have a sizable investment that you hope will pay for your retirement you might want to go for the solid 10% yoy. Similarly if you manage other people's money they might be unhappy with you making 50/50 bets with that money.
It's the same logic that causes people to buy lottery tickets. Winning big in the lottery is unlikely, but getting rich by saving two lottery tickets worth of money each month is impossible. The risky strategy with the worse expected outcome is the only one that leads to your goal.
Time scale yeah. I may do a bond tent when I get closer to retiring. But given the same amount of time and different amounts of money, if my cost of living is covered either way, why use a different strategy?
It does work at small scale and people don't stop, make careers and billions out of it, see high frequency trading. You can play market timer yourself just by using some game theory and keeping up with the chart.
So your investments could be used to screw other people out of their money who are similarly financially illiterate/insecure?
It’s kind of crazy to me that there are somehow still staunch cryptocurrency proponents out there who have somehow ignored all the negative press it has received.
By dominant media narratives you mean a self evident train of scams and security incidents? There's no conspiracy or undue effort to make crypto look bad, that happened in a decentralized manner.
> a self evident train of scams and security incidents
Because a bunch of bad people jumped on the bandwagon to exploit others.
Bitcoin != “crypto”
Bitcoin was the original and it’s still here. And it will continue to be here.
The goal of bitcoin is not to “make money”. Bitcoin is money. A new kind of money. One that no central entity can control. One of which there will only ever be 21,000,000. No one can print more Bitcoin. Unlike fiat, which the government and the ruling class use to screw people over right in front of their faces all in broad daylight.
Bitcoin can not be diluted. Bitcoin can not be inflated. Bitcoin can not be controlled. Bitcoin can not be stopped.
Fiat is weak money. Fiat is bad money. Bitcoin is strong money. Bitcoin is good money.
> The world's top Bitcoin mining pools mainly come from China, with five pools being responsible for more than half of the cryptocurrency's total hash.
I am US-based and run one of ~8,000 global bitcoin verification nodes (i.e. not a miner). No majority of these nodes are based in any specific country †.
You should probably better educate on bitcoin protocols/mining before you go spouting off unfamiliar stats.
I don’t think that answers the question. Denying transactions is certainly an issue. If it is true that the majority of mining power is in China, only a minority is outside of it. What mechanism does Bitcoin have for a minority of nodes to deny the transactions of a majority of nodes?
The "verification" nodes don't do anything to prevent censorship by miners.
The threshold isn't quite 50%+. If one of the 49% nodes mines a block with a would-be censored transaction, the censoring notes have to make an economic decision to try to mine a replacement block and then a second block on top of that to rewrite the chain. At 100% this is easy, but at just 51% it's a costly gamble that will frequently fail at a huge dollar cost.
A block costs $200k at current prices. At just over 50% of the network, you are gambling at least two blocks to force a rewrite.
>The "verification" nodes don't do anything to prevent censorship by miners.
Absolutely agreed; however, eventually some non-hostile miner will randomly generate an acceptable `nonce` [entire point of hashing/energy-usage] which DOES include the censored-by-some transaction.
An additional function of the node-verification network (which uses essentially no energy, relative to mining) it to maintain the entirety of `mempool`, which is where unaccepted transaction-attempts live until mined into a block [which is then "accepted/denied" by same node-pool].
tl;dr: as far a probabilities go, unless you own exactly 100% of mining pool, it is impossible to censor a tx from the node's mempool; all you can do with <100% is DELAY transactions.
> One of which there will only ever be 21,000,000.
This is a good property of something you want to be scarce, but it's a terrible property for money, whose purpose is to exist in the correct amount to keep stable money velocity in a growing economy. (Or a shrinking one.)
There's a very simple change to the reward function that fixes this: make block reward proportional to difficulty. There's a real implementation called Ergon. I wish everyone wasn't so poisoned against it now that it was possible to talk about interesting ideas without sounding like all the scammers.
The original people who were involved in Bitcoin had gold bug mentality and that directly created the early adopter advantage that makes Bitcoin so unfair.
All it takes is 100% node concensus (e.g. a hard-fork for any non-agree-ers).
Hell, with Entirety-Approval, we could also increase the 20.99999999 limit (it's just a concensus-node rule; all that's needed is agreement).
As the operator of a node for over a decade, now, I do foresee a day when 1 Satoshi [i.e. 0.00000001 BTC] is no longer the smallest divisible unit... one day, perhaps beyond my lifetime, there may be mille- and eventually even nano- Satoshis.
Except anyone can start a parallel chain, e.g. DogeCoin. The only thing that makes BitCoin special is that it was the first and is still the most well known. It's value is entirely based on network effects and speculation. It's a speculative store of value which can be digitally transfered for a modest fee.
Fiat has the force of the state behind it. This has pros and cons, depending on perspective and use. As a currency, it's superior in many ways. As a store of value, it's in many ways inferior to BitCoin... Until it's not.
Bitcoin is too volatile to be a store of value and too slow and expensive to be useful for transactions. It is public so it is not even great for illicit transactions.
> Fiat is weak money
Try explaining that to the IRS when they ask for taxes in dollars.
> Bitcoin is a force of nature
Asteroids are also a force of nature. That doesn’t make them good.
> Try explaining that to the IRS when they ask for taxes in dollars.
If Bitcoin became the most recognized and popular currency, it is conceivable that tax authorities like the IRS might start accepting taxes in BTC. Of course it would require legislative changes, and lots of effort and work put into valuation and conversion, collection and storage, auditing and compliance, and public education.
Sure, any currency can experience a liquidity crunch. This is a macroeconomic phenomenon. The main purpose of a central bank's massive currency reserves are to provide liquidity in the event of a liquidity crunch.
For simplicity imagine that there are just a few institutions that hold the majority of Bitcoin. Now imagine all of them are incredibly over leveraged on risky financial assets that suddenly all go to zero. Each of these institutions needs to suddenly pay off massive debts that they can't afford, and they start to spend their full Bitcoin reserves to pay. Investors notice the institutions are going belly up and simultaneously try and withdraw all their bitcoin deposits. There simply aren't enough Bitcoins to go around and the financial institutions holding bitcoin collapse.
When this happens in normal currency markets, the Federal Reserve steps in and provides a bail out of temporary liquidity to cover some of the debts involved for long enough to calm down investors so that everyone isn't simultaneously trying to cover massive debts with the same insufficient supply of currency. This is an absolutely critical part of modern macroeconomic stability. Every liquidity crisis that has happened would have been massively worse if not for this "monetary stimulus."
Media narratives and conspiracies are often used interchangeably, I can't read your mind so I included both. Also in your original comment you brought up the media, it's right there, so...
dude the comment i responded to is from you saying "cryptocurrency proponents out there who have somehow ignored all the negative press it has received."
In fairness, that was actually me. May want to double check the usernames. Both start with ch - easy mistake to make.
I would have participated more in the discussion but HN is telling me I’m posting too fast so I’m guessing a moderator didn’t like some of my harsh tone.
Can't have been trained on hackernews then, this is the most anti-crypto space I'm aware of besides /r/buttcoin. i'm also softly anti crypto so not criticizing, just pointing out you're literally in an environment where the opinion you're talking about gets eviscerated every time so it can't be what "everyone is saying"
I agree about the love of novelty, but two of your examples (Tesla/Musk, LLMs) are also falling out of favor in mainstream news. Especially Elon since Twitter. LLMs too (or at least the hype surrounding them as AGI) have seen mainstream panning of late, in parallel to mainstream outlets
I don't think it's about novelty - heck people here will praise Unix and C regularly.
It's more that crypto initially had potential, at this point it's been tried and failed to deliver - at least from the value perspective of people here.
I turn 40 this year, and somehow have managed to entirely not touch my meager HODLings since 2018... it's the only reason I still earn USD (i.e. to not cash out any bitcoin).
I'm not rich, yet... but it's been a WILD. fucking. ride. (even just so far). Personally, I cashed out my entire 401(k) in 2016 and invested half of it into Bitcoin... which helps to not spend anything, viewing it as "my retirement, hit-or-miss..!"
I think lately results of chat went downhill. I got used to asking "are you sure about that" after each chat answer to my question, and to most of the time the answer is "you are right, here is how I was wrong".
That's not a recent thing - most of the LLMs I've tried have an annoying tendency to agree with you if you question them, even if they weren't actually wrong. The term for it is "sycophancy", I think there are a few papers that talk about it.
This reminds me of some communications training where they were saying that the most things are not worth disagreeing on and just agree with whatever.
And I think I read in some parenting books too that it is not worth correcting kids over things that don't matter like if they say dinosaurs and mammoth were alive during same time. Over-correcting hurts their confidence.
Maybe LLM been trained on these ideas or maybe it is start of science fiction nightmare and AI really think that it is not worth arguing with mere humans.
Ask a question like “Why do EVs use less electricity per mile when it is 100 than 70 degrees outside” and then reverse the question.
You’ll get two answers that totally contradict each other.
“Electric vehicles (EVs) use less electricity per mile in warmer temperatures (around 100 degrees) compared to cooler temperatures (around 70 degrees) primarily due to the following reasons:
1. *Battery Efficiency*: EV batteries operate more efficiently in warmer temperatures. Cold weather can reduce the battery's ability to hold a charge and increase internal resistance, leading to higher energy consumption.
2. *Thermal Management Systems*: In cooler temperatures, the EV’s thermal management system works harder to keep the battery at an optimal operating temperature, consuming more energy. Conversely, in warmer weather, less energy is required to maintain this temperature.
3. *Reduced Heating Requirements*: When it’s around 100 degrees, the need for cabin heating is eliminated, whereas at 70 degrees, some heating might still be required for comfort, consuming additional energy.
4. *Air Conditioning Efficiency*: While air conditioning is used more in hotter weather, modern EVs are designed to be highly efficient in cooling compared to heating, leading to lower overall energy consumption even when the AC is in use.
These factors combined result in lower electricity consumption per mile in warmer conditions compared to cooler ones.”
Reversed:
“ Electric vehicles (EVs) use more electricity per mile in extreme temperatures (both hot and cold) due to the increased energy demands of their climate control systems. Here’s why:
1. *Air Conditioning in Hot Weather:* When it’s 100 degrees outside, the EV’s air conditioning system has to work harder to cool the cabin to a comfortable temperature. This requires additional energy from the battery.
2. *Battery Cooling:* High temperatures can affect the performance and longevity of the battery. To protect the battery, the EV’s thermal management system will actively cool the battery, consuming more electricity.
3. *Increased Resistance:* High temperatures can slightly increase the electrical resistance in the battery and other components, which can lead to marginally higher energy consumption.
In contrast, at a moderate temperature like 70 degrees, the demands on the air conditioning and thermal management systems are much lower, resulting in more efficient energy use.”
This type of behavior seems like it should be something that should be (relatively) easy to fix with some kind of external intervention layer. Google has been able to answer queries without using LLMs for some time now, so maybe some kind of pre-check followed by a prompt injection to stiff-arm the LLM in the right direction.
Whenever you're building some ad-hoc non-differentiable circumstantial hacks around your learned model (regardless of whether it's an LLM or not), two alarms should go off in your head;
a) Could this be made differentiable? End-to-end systems are nearly always stronger than systems made up of multiple models or models-plus-heuristics;
b) is it appropriate to be using a statistical model here at all?
External intervention layers are generally severe technical debt.
Yep, that’s how it works. LLM’s like to make lists. They could make lists of supporting reasons for just about anything. Unless it’s trained into them, they don’t have an opinion, they have all the opinions.
I don’t understand how this is a surprise to so many people. The thing can’t reason. If you point out an error, even if it’s real, the GPT doesn’t suddenly “see” the error. It constructs a reply of the likeliest series of words in a conversation where someone told it “you did X wrong”. Its training material probably contains more forum posts admitting a screw-up than a “nuh-huh” response. And on top of that it is trained to be subservient.
Because it doesn’t _understand_ the mistake in the way a human would, it can’t react reliably appropriately
It makes it difficult to get less-biased responses. I find myself asking an affirmative-worded question and its affirmative-worded inverse to subtract out the sycophancy. It's a poor workaround.
That is because they turned the sycophancy up to 11. You have to turn it down, if you are a serious LLM user and you don't have your own system prompt, you are using it wrong.
Love this idea. Would be great to see how it applies to twitter (e.g. reduction of tweets during GPT outages) but I guess that twitter data is hard to get now
1. Set up LLM to give financial advice on which stocks to trade.
2. Secretly read the results and use the information to make your own trades
3. Profit!
It could be news parsing, where it can turn news article text into data points that an investment model could imply market signals from.
Something similar could happen with transcripts of company investor calls, or any other text/audio companies put out. With the right prompt you can turn text into signals, the trick would be getting that prompt right (and prompt engineering to limit hallucinations as much as possible).
Or you can just not use ai and build your own sentiment analysis metric that is actually going to work. E.g. maybe you make a word cloud of a bunch of recent news articles, you identify certain candidate words as positive sentiment or negative sentiment. Now you can score any new article by counting pattern matches with either list. Not really much initial work to set up, and you probably get much higher quality results than what hallucinating ai would get you, if you happened to find that magic prompt that is.
Since 2016, our mutual friend and I have been adamently suggesting he look into "this bitcoin thing" — his response was typically [disinterested].
At a recent breakfast, it was explained how "talking with ChatGPT finally convinced [him] that you guys have been correct about Bitcoin all along."
When asked "what did ChatGPT explain to you that we two humans could not?!"
His response was simply "I never got embarrassed asking the computer any finance questions, even stupid/simple ones; I've always been the finance guy with answers so I forgot how to be humble in unexplored topics."
Pretty damn humbling, indeed; now if only he had listened back in 2016 =D
†: "Time in the market beats timING the market."