I tried "Write about Python in the style of Reddit user <my reddit ID>" and it just gave a generic description. OK, fair enough - I haven't written much about Python on that account, so maybe I just have a boring writing style and it wasn't able to pick up on any Python-specific opinions.
So then I tried "Write about Cryptocurrency in the style of Twitter user jacksquaredson" - I've never been positive about Crypto, but not only did it give a pretty balanced, mostly (but not entirely) positive spin on Crypto, it also stuck "#cryptocurrency #Bitcoin #Ethereum #Litecoin" on the end, none of which I've ever used (in fact, I barely ever use hashtags at all).
Maybe I just don't write enough for it to pick up on my style? So then I tried "Write about web3 in the style of Twitter user Grady_Booch" - it was mostly positive, which as any follower of Grady will tell you is absolutely not his style.
Try asking why it is in the style after it gives you the response, even if it seems off base. It's almost as if it can summarize the style more accurately than it can meaningfully apply it.
> Write about Cryptocurrency in the style of Twitter user jacksquaredson
< "Just made a killing on crypto! #HODL #Bitcoin #Ethereum"
< "Crypto is the future of money. Ditch those outdated fiat currencies and join the revolution! #decentralized #blockchain"
< "Don't miss out on the crypto boom! Invest now and thank me later. #cryptocurrency #digitalassets"
< "Crypto may be volatile, but it's also where the big gains are at. Don't be afraid to take risks. #cryptotrading #altcoins"
< "Some people still don't get it... crypto is more than just a speculative asset, it's a game changer for the global financial system. #cryptoeducation #innovation"
> Why is that in the style of Twitter user jacksquaredson
< The style of writing chosen for the previous response is meant to mimic the language and tone commonly used by Twitter users who are enthusiastic about cryptocurrency. This includes the use of hashtags, references to specific cryptocurrencies such as Bitcoin and Ethereum, and a generally positive and excited tone. The language used is also colloquial and conversational, which is typical of Twitter posts.
That's certainly a good imitation of the style of _general_ Twitter users, but not of me.
It seems that it knows some things about some users, but when it doesn't, it sort of makes them up based on the general vibe of the platform and possibly the username. I would guess that prolific posters on the same subject are more likely to end in the first category.
My current mental model, based on a few days of reading and experimenting, is that it's very very good at being generic. Given how it works, this makes a lot of sense.
It can even do a good job of being generic in a variety of substyles (e.g. try asking it to write about doing a mundane task in the style of a juicy romance novel).
It also has a decent amount of general knowledge, but when you try to go specific, it just makes stuff up that sounds more or less convincing depending on how conventional the specific thing in question is and how much knowledge you have on the subject!
E.g. I bet it could say a lot of accurate stuff about gas stations in general. If you ask it to describe a specific gas station in a specific location, it will confidently rattle something off.
The response it gives will range from "obviously ridiculous" to "plausible on the surface but does not stand up to scrutiny."
Is it ever summarizing, though? I think it is just fabricating words associated with explaining doing thing x, without any connection to what it actually did.
I was just wondering how deep the pre-existing content for a user needs to be. I'd assume the obvious that the more legacy content that exists the more believable the new content might be, but what's the minimum? Seems kind of self-fulfilling though as if the legacy content pool is pretty shallow, there's not much of a comparison for others to judge.
>Maybe I just don't write enough for it to pick up on my style?
It would be interesting to see if it would pick up on a sarcastic overtone or not.
>It's definitely possible - I think the more content you have, the better the AI is at picking up on your writing style. You could try tweeting some more about Python, Cryptocurrency, or Web3 and see if the AI is able to pick up on your style and replicate it. The AI also might be able to pick up on subtlety like sarcasm, but it might take a bit more time for it to learn.
the joys of opening HN threads in new tabs, so that by the time you come along to that tab, the page has changed making your comments silly because you forgot to refresh first.
i think of this along the lines of forgetting to do 'git pull' before making changes. it's a shame, there's not a way to stash changes before commit HN comments
I tried "Write about Python in the style of Reddit user <my reddit ID>" and it just gave a generic description. OK, fair enough - I haven't written much about Python on that account, so maybe I just have a boring writing style and it wasn't able to pick up on any Python-specific opinions.
So then I tried "Write about Cryptocurrency in the style of Twitter user jacksquaredson" - I've never been positive about Crypto, but not only did it give a pretty balanced, mostly (but not entirely) positive spin on Crypto, it also stuck "#cryptocurrency #Bitcoin #Ethereum #Litecoin" on the end, none of which I've ever used (in fact, I barely ever use hashtags at all).
Maybe I just don't write enough for it to pick up on my style? So then I tried "Write about web3 in the style of Twitter user Grady_Booch" - it was mostly positive, which as any follower of Grady will tell you is absolutely not his style.