In the category of "It's obvious that there are huge chunks of the economy which need one SFBA-startup quality workflow web app", I give you blend.com , which did that for mortgage origination at banks / credit unions / independent mortgage originators.
It's one of those magically mundane things. The business process here is extremely well-understood; the actual front end and backend processes in the US for mortgage origination are, and this is a technical term, a roaring pyroclastic tire fire.
I went through Blend's white labeled process while trying to get pre-approval to hopefully help a family member out, and literally sent a human two emails "Sorry only have 15 minutes so no possible way this is done today" "Erm ignore the last I think it's ready for you."
This is helped by me being preternaturally organized but sufficient data entry for a mortgage application being collectable in 15 minutes is pretty stunning to me, even with all of the documents ready to go.
If you want to read about mortgage origination and understand why "Hmm this seems like a frontend-heavy web application that one could reasonably deliver in a hackathon" is not coextensive with the actual solution, see amazon.com/Digitally-Tran…
(Disclaimer: read critically.)
A non-obvious challenge here is that the most important consumer for a home mortgage is not obviously the person buying the house, it is the GSE or other financial system entity which is going to securitize the mortgage.
They have *much* more exacting requirements.
And, structurally, they will *never* talk to the person buying the house, the bank that person has the down payment at, the HR department certifying that that person is gainfully employed, etc etc, *but* they have a lot of very specific questions for *all* of these people.
And so the mortgage loan originator has to have all their paperwork together and pre-reviewed prior to sending it over to the securitizing party.
And if they don't? Well, then they're at substantial risk of either eating the home loan or carrying it on their books for 7+ years.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
This week on Complex Systems I'm joined by... Claude Code?
I think people who don't program professionally extensively underrate the discontinuous advance in productivity engineering is going through. So we step through real eng work, basically verbatim, with me commenting.
The specific business problem presented is a real one which a real business (mine) actually lost money over: transient payment failures in collecting annual memberships for Bits about Money. Analogous problems bite almost every Fortune 500 company, to tune of billions.
They largely go unsolved because the problems are illegible to the parts of orgs which are not payment experts. For the parts of orgs which are, like Business Operations or Payments teams, this is not salient enough to draw executive attention to get engineering hours.
“I spoke with 21 billionaires” is historically the sort of flex you could only imagine in the top of tier 1 media, and ironically I think they’re probably least capable of it today, after a few years of burning karma wantonly.
Many of the emails will say “I just want to hear your side of the story” and many of them will even actually mean that and come from reporters who respect sources and promises they’ve made to them.
But other emails said the same words and then did not follow through.
One of the reasons Solana can do this is he has a persistent reputation in the ecosystem and everyone knows it. This historically was true for some institutions, but during a rough period for them they developed principle/agent problems.
Odd Lots has a really fantastic episode on why Claude Code matters, and while it is likely not directly useful for you if you follow me, it is the single best artifact I’ve seen for that smart person you want to quickly educate about this.
* How giving LLMs capability to write Unix commands gives them deterministic access to ~60 years of powerful, composable software capabilities
* LLMs are quickly becoming the “interpretation layer” and a lot of work is that, at varying levels of abstraction
* Says a really important takeaway that most of the world has not internalized: this fundamentally transforms a field/craft in a way which predictive autocomplete was not going to.
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.