Ruriko: So when do we register with Chicago?
Me: We don’t.
R: So how does Chicago know everyone who lives in Chicago?
Me: It doesn’t.
R: … Does America have a government? How do you even do population statistics?!
Me: Count every ten years.
R: You ARE TROLLING ME.
The last few minutes have been her working through the implications for every benefits program administered locally, with increasing levels of horror.
Ruriko: Wait you mean Chicago Public Schools literally does not know Liam and Lillian exist unless we tell them that.
Me: Yep.
Ruriko: So there’s no form to tell them that we are putting our children in private school?
Me: No form.
Ruriko: So if a child is just not enrolled they…
Me: Hopefully are seen by truant officers who will eventually cause someone to ask about the circumstances.
Ruriko: TROLLING.
Ruriko: Next you’re going to tell me the national government doesn’t have a record of everyone who lives here.
Me: In practice it does but in principle it does not.
R: WHAT.
Me: It is considered politically unpalatable to create a list of all citizens and/or immigrants.
R: WHY.
Me: … So that is why we backdoor the problem with a combination of Social Security records and privately maintained credit databases.
Ruriko: STOP STOP STOP.
Ruriko: But if city hall doesn’t have a record of us living how will your employer be able to identify you to them to pay taxes for your account.
Me: They don’t keep accounts that way. Employers don’t do taxes, though they will do withholding. We will self-file and then if…
Ruriko: … Is our marriage even legal here?!?
Me: Yes.
R: Where did you register it if not city hall?!
Me: Nowhere.
R: Then how does America know we’re married?!
Me: When relevant, we say so, and they say “OK then you’re married.”
R: WHAT.
Me: Doctrine of comity.
Ruriko: So if we got married here we would have… a piece of paper.
Me: Yes it’s called a marriage license or somesuch.
R: We are unlicensed.
Me: Yes but only in a very technical sense.
R: Can we get a license?
Me: No.
R: What.
Me: People w/ existing marriage can’t get married.
Ruriko: What if I have to demonstrate the fact of the marriage somehow?
Me: Well there’s a boring technical answer involving apostilles to authenticate a series of records which would allow an American judicial process to recognize Japanese records but in practice…
Me: … everyone just takes your word for it.
Ruriko: … You are dealing with all of this American nonsense.
Me: Had a feeling I would be.
Ruriko: … How do you do health insurance?
Me: Hah funny you should ask. Let’s have that conversation when you’re calm and sitting down.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
In many domains a generalist who is good at AI and puts an hour or two into something will be three to four sigma from the mean entrant into a support / escalation / etc inbox.
Mitchell has an example from bug reports; I can easily imagine examples from e.g. financial issues.
I think *once* when doing advocacy work for people with banking/credit problems I ran into someone who had an organized call / letter log and so could cleanly generate a timeline that the financial institution could match up with their own files (and obligations).
Try it if you don't believe me but if you give AI a bunch of unstructured input like most people's impressionistic account of how this has been so frustrating dealing with the bank, they will frequently redigest it into "Here's a timeline with bullet points."
Considering writing about non-coding LLM workflows a bit in December partially for personal interest and partially so people can see concrete examples of progress / usage.
The one easiest for me to talk about is just a geeky hobby: here's a plastic model and then here is ChatGPT producing a painting reference of ~that model, after a discussion on characterization, color scheme, etc.
I honestly love using it in my art projects. Hallucination rate is acceptable given ~wide acceptance criteria in art; like Bob Ross used to say, there are only happy accidents if e.g. its suggested recipe for mixing a teal paint does not actually result in teal immediately.
If I clipped every good Byrne Hobart or Matt Levine line I’d never get around to writing my own stuff but this from Byrne is too good to not share:
An extraordinary fact about finance is that there are some firms which are financial service providers specifically for scams which sometimes, almost as an industrial accident, bafflingly end up in a contractual relationship with a legitimate, successful company.
These underwriters are not necessarily that; some overlevered highly “structured” IPOs of midmarket software businesses should have a non-zero price, and a capitalist should not say they are a scam just because he is not a buyer at that price.
How much could would you write if you could one-shot 10-100 line shell scripts or similar almost all of the time, in 10 seconds? You would write a stupid amount of code. Who cares if it is disposable? Dispose of it; it's basically free.
Skill issue, code is free to you. Write a test suite too, designed to be thrown away in under a minute. Write three independent implementations and vote on the answer. etc, etc
"Have you actually done this?" Yeah, to a minor degree, and I'll recount a bit more when I do some writeups about my experience with LLM programming. After a few weeks of climbing the skill curve instead of some direct questions I'd say "Goal: *direct question* You should..."
Me to financial firm: *address change form*
Financial firm: Is this five digit number a post code?
Me to financial firm: Oh you have asked exactly the right person for geeking out about post codes. Did you know...
Second thoughts: That was not the efficient way to answer.
"Why didn't they know what a post code looks like?"
Because a post code can look like so many things, like 100-0001, 20500, or SW1A 1AA, to use three codes from three nations that all correspond to a particular famous building/complex within them.
A further fun fact: some nations don't customarily use post codes and others don't customarily use addresses, favoring a natural language description of the recipient which is sufficient to get a mail carrier to successfully route to them.
Still working on a few essays about what I learned on using LLMs for coding but if you want a sneak peak, Complex Systems this week discusses the game I made in some detail.
I’m probably adding one essay to the series on LLMs for taxes.
It feels a bit weird to need to continue saying this, but yes, LLMs are obviously capable of doing material work in production, including in domains where answers are right or wrong, including where there is a penalty for being wrong. Of course they are.
“Why?”
Because a lot of discourse weights people and actors heavily where they cannot be right or wrong in any way that matters, and where correctness does not materially result in a different incentive for them.