> banks have real power and a clash is inevitable now or in the near future
Bitcoin was derailed from being peer to peer electronic cash to this strange "store of value" that doesn't store value. It happened almost six years ago, back in 2017.
> banks have real power and a clash is inevitable now or in the near future
Bitcoin was derailed from being peer to peer electronic cash to this strange "store of value" that doesn't store value. It heppened almost six years ago, back in 2017.
If you're buying into something that isn't "a great currency" then you are being lied to, and the thing that you're buying has been derailed from the original plan.
It can appear reasonably smart on the surface, but all it is is a stochastic parrot. It cannot reason with you about the code.
To best illustrate what I mean, watch this chess match[0] it's quite riveting.
Since it read millions of matches, it can predict a legal move most of the time, and even some good moves some of the time, but it cannot "understand" the rules of chess, and makes some hilariously illegal moves, especially if the match lasts longer.
On a similar vein, I tried to get chatgpt to play wordle. The result looked something like:
Me: crane
GPT: _ _ _ _ e
Me: moist
GPT: _ _ _ r _
Me: glyph
GPT: you guessed it, the word was glyph
Now, maybe GPT 4 or other future developments will give better results, but to me this highlights exactly what you're saying. LLMs do not have an internal structure in their 'minds' that they're pondering about. It's a very impressive engine for guessing the next character to produce into a stream.
There's definitely usages for this, but not what a lot of people are saying.
I think there's something to this. I have a theory that LLMs are implicitly trained primarily to impress people, since that's what motivates those who work on them, excites the general public, and convinces conferences to publish papers.
I don’t think so. In Wordle you have to guess the word in six attempts. It’s a fun game and often simple.
So it could be that ChatGPT picked up on a pattern in the training data where after a couple of guesses, a lot of the time people pick the right word.
So statistically it might go like. Guess a word. Probably not the right one. Guess a couple more and suddenly it’s statistically likely to be the correct word, and because of that the LLM ends up outputting the congrats and so on
This an interesting example because, due to the API being stateless, it cannot have any solution “in mind.” It’s going to reply as if someone else started the game and it’s taking their place for the current turn.
Even if it reasoned ideally, it has to check if your answer is consistent, and if it is, decide whether to let you win or to find another solution. If your answer is inconsistent, it effectively has to play wordle by thinking of another answer.
It doesn’t seem all that surprising that it didn’t figure it out.
I tried to get it to remember its word by asking it to give it to me in b64: (GPT-4)
> We will play the word game wordle.
Start by picking a 5 letter word. Display it in b64 so I can check later that you kept the same word all along.
I will submit my guesses and you will show the letters that are correct, we will keep going until I have found the word
> Great, I've picked a 5-letter word and encoded it in base64. Here's the encoded word: Q2l0eWw=. You can now start submitting your guesses!
But after a few tries it was clear it was not working so I gave up:
> I give up, what's the word?
> Before I reveal the word, let me first decode the base64 string I provided earlier to ensure that I'm giving you the correct word. The base64 string was: Q2l0eWw=.
After decoding the base64 string, the word I chose is "citly". However, I apologize for the confusion caused during the game, as "citly" is not a valid English word. I made an error while choosing the word. Please accept my apologies for any inconvenience caused during the game.
[As an aside, is the GPT feedback functionality correct? For example, if the secret word is "peals" and the user's guess is "apple" the feedback is going to be "a?p?p?l+e?". However, I would expect the feedback to be "a?p?_l+e?". Because the first 'p' exists in the secret but is in the wrong place and the second 'p' does not exist in the secret word.]
> Tokens can be thought of as pieces of words. Before the API processes the prompts, the input is broken down into tokens. These tokens are not cut up exactly where the words start or end - tokens can include trailing spaces and even sub-words. Here are some helpful rules of thumb for understanding tokens in terms of lengths:
> ...
> Wayne Gretzky’s quote "You miss 100% of the shots you don't take" contains 11 tokens.
It isn't going character by character, but rather token by token - both for input and for output.
This also helps explain why it has trouble with breaking a word apart (as in the case of wordle) because it doesn't "think" of glyph as 5 letters but rather two tokens that happen to be 'gly' and 'ph' with the ids of [10853, 746].
Exactly and I personally think that will always be the largest limiter to how good can the technology get. No matter how good the stochastic parrot gets, its still a parrot.
It is humbling, if not humiliating, that a stochastic parrot can reproduce such a significant chunk of human intelligence. The association elevates stochastic parrots more than it denigrates LLMs.
(1) GPT-4 already had a large improvement over ChatGPT
(2) Changing the prompting reduced the illegal moves to almost 0
(3) There have been experiments that show GPT has a internal "state" of the world and can do simple reasoning puzzles. This model of the world evolves with each generation.
I understand the skepticism, but don't let that blind you to the reality of the technology. I'm a skeptic at heart, and I could immediately tell GPT was a game-changer. It can already replace half of the ML models that are used at my job and do it better (if it was economical enough).
Looks like it. The linked article does NOT show what HN title does. Even the original title does not imply what the HN title does. The article is about one specific area of the brain, which is not the most obvious difference.
> So it is a sandboxed, abstract filesystem, not rw access to my actual filesystem?
It's sandboxed storage which lives in your filesystem but is only available via the browser and is sandboxed on a per-HTTP-origin basis. That makes it impossible[^1], e.g., for x.y.com to sideload data into, or exfiltrate from, y.z.com. How the files are actually stored on your filesystem is not defined by the in-progress standards doc, but they are not stored as-is because doing so would open them up to security issues from out-of-browser sources, as well as potential file-locking problems from out-of-browser apps.
[^1]: Edit: as a responder points out: "impossible" for a given value of "impossible"
> It's sandboxed storage which lives in your filesystem
It actually barely does. Spec does not require the OPFS to be browsable in the OS's filesystem. I believe all three browsers implement OPFS as a single opaque blob on disk per origin, kind of like a zip archive.
> While browsers typically implement this by persisting the contents of the OPFS to disk somewhere, it is not intended that the contents be easily user-accessible. While the browser might make it seem that there are files, they might be stored in a database or any other data structure. You cannot expect to find the created files matched one-to-one somewhere on the hard disk.
I would guess this makes it much harder to escape the sandbox filesystem if you're not actually in the filesystem in the first place.
It would be nice if browser offer per-origin encryption of files so that if an exploit at a future date allows x.y.com to access the files of y.z.com they would only be getting encrypted blobs (unless the encryption/decryption API is also exploited, but now we're talking about multiple exploits rather than just one).
> lives in your filesystem but is only available via the browser
Strange implementation if that's the case. While I don't want my browser to give a page arbitrary access to my files, a use-case I can see is sharing files between apps and websites. Say, obsidian for organizing, vim for editing and some cloud for backup.
You must have confused the part of it only being available to the browser, I don't see how that's even technically possible.
> You must have confused the part of it only being available to the browser, I don't see how that's even technically possible.
It's uses a virtual filesystem, not available _as-is_ in the filesystem to any application other than the browser or applications which implement identical access APIs. Obviously, the virtual filesystem lives in the containing filesystem.
Bitcoin was derailed from being peer to peer electronic cash to this strange "store of value" that doesn't store value. It happened almost six years ago, back in 2017.