eob

Bit of a side question to the crowd:

If anyone wants to commission an AI novella, holler out to me. (For free -- this is a hobby)

I've been trying to build an automated book publisher for about a year now. While the books aren't yet "human good", the slop factor is getting fairly low. Part of that is because I've stuck to formats easier for AI to avoid the uncanney vally in: recipe books, historical re-tellings, etc.

With the speed of vibe coding.. I'd expect the "Reverse Engineer Anything" folks to come out with a "Man in the Middle Anything" app by lunch

A lot of us here are VC minded hackers *because* we spent years of our lives working minimum wage jobs in academia and then eventually realized we preferred to build!

Rest in peace Bob. One of the great early tech writers. The feeling of his writing -- the blend of fact and opinion and sense of humor, and more than anything the sense the really cared -- always felt to me like one of the seeds that developed into the blogosphere.

Simon I hope from this day hence, your bio always includes:

"Simon Willison, among other things, is an advocate for the inclusion of pelican geometry in LLM training datasets."

I think because you don't know /which/ developer you're going to get.

One interesting aspect of LLMs is that each one, weights frozen, can be thought of as a single developer whose work you have already evaluated.

The cost of finding, evaluating, and negotiating with a new human is tremenous.

These comments are so filled with cool projects and visualizations I’ll throw my own out there:

Trying to generate non-slop, print-worthy recipe books for different diaspora communities.

www.robotbookclub.com

I’m pretty sure the recipes have surpassed slop. The photos are pretty close. The layouts, intros, and “chef photos” need a lot of work though.

This is how I write down recipes for myself! There’s got to be some cognitive archetype that works better with this style encoding.

Do you have any suspicion about what is different between the backends?

That's an absolutely bonkers statistic: it would mean spurious differences in hosting container overwhelm the performance differences between models.

My guess it's just the emergent behavior that results when a company doesn't provide developers time to fix bugs.

If their week is already booked full just trying to keep up with the roadmap deadlines, a bug ticket feels like being tossed a 25lb weight when you're drowning.

You could say: "but have pride in your work!"

But if your company only values shipping, not fixing, that attitude doesn't make it through the first performance review.

You think like a person who’s debugged large systems failures before :). That feels very plausible.

Some outlets reporting T-Mobile and ATT as well.

I assume state on state cyber attacks are commonplace but get minimized to avoid public fear.. perhaps this will be the first notable one.

I build coding agents for a living, and I'm struggling to map this onto the set of things I do at work.

In general, interoperability and user choice are really important for us to get right as the community of people building AI platforms...

Have others reading this document been able to map it onto their work?

As a specific example:

> ai://bank/service/payments?amount=10&currency=USD

I'm not sure what this is representing here. Is it a way to encode a clickable link to chat with `bank` about `service/payments` with a few additional args attached?

Third party apps can’t use the network though. Iirc there’s an async message queue with eventual delivery that each app gets, which it can use to send messages back and forth with a paired phone app.

Bravo -- this is fantastic.

I've been waiting for this ever since reading some interview with Orson Scott Card ages ago. It turns out he thinks of his novels as radio theater, not books. Which is a very different way to experience the audio.

Or vice versa - perhaps some subset of the "thought chains" of Cyc's inference system could be useful training data for LLMs.

An aspect of these self-improvement thought experiments that I’m willing to tentatively believe.. but want more resolution on, is the exact work involved in “improvement”.

Eg today there’s billions of dollars being spent just to create and label more data, which is a global act of recruiting, training, organization, etc.

When we imagine these models self improving, are we imagining them “just” inventing better math, or conducting global-scale multi-company coordination operations? I can believe AI is capable of the latter, but that’s an awful lot of extra friction.

Are you comfortable sharing the video & lip-sync stack you use? I don't know anything about the space but am curious to check out what's possible these days.

This looks fantastic — congrats on the launch.

As an armchair observer, the agents + browser space feels like it’s waiting for someone to make the open source framework that everyone piles on to.

Proxy rotation sounds like a solid way to monetize for businesses.

There was an SF office of 18F -- IIRC it was in the building to the right of the Civic Center park as you looked at it from the Bart stop. They were great folks from every encounter I had with them.

Let's presume this gets developed to ShadCN/Tailwind level quality.

In that world, what would be the tradeoffs between:

- NextJs + Tailwind + ShadCN

- NextJS + ?? + Shoelace

I don't have a good sense of how web components compare to practice of "copy-by-value, then compile-into-binary" UI shipping that's common in the Next + Shad world these days.

Have you ever managed a complex, dynamic, changing system and found that the optimal size based on current conditions was 20% less than it was at some prior time?

I can think of all sorts examples.