Tom Lieber's Microblog

alltom.com, Archive, Currently Reading, Have Read, Micro.blog
Subscribe with RSS or @tom@micro.alltom.com

Oct 26, 2024

I think it’s funny that tapping repeatedly and long pressing are mapped to power user features because that’s what kids do first and it just wreaks havoc on computer systems as a result.

The wild thing about programming with LLMs is documenting a function’s runtime cost in big-O notation and USD. “Costs $0.50 when N is 40.” I have faster and cheaper versions of that one, but I haven’t figured out how to make them as good yet, and that choice filters all the way to the UI. 🫠

Jul 22, 2024

“Do I have any events this week that it looks like I forgot to add to my wife’s calendar?”

😭 The future is beautiful.

Jul 21, 2024

I keep finding new uses for letting LLMs generate calendar files, but today I wanted to close the loop! I want it to read and write to my calendar directly.

So to start, I provided the LLM a “tool” to access Google Calendar’s ListEvents API. Just being able to read my calendar is pretty neat:

Q: What events do I have today?
Tool use: Get today’s events
A: A bulleted list of event names and times, followed by a summary like, “Looks like it’s your usual daily routine, with a trip to the museum in the morning.”

Q: Of breakfast, lunch, and dinner, which do I already have blocked out?
Tool use: Get today’s events
A: Breakfast for the kids is on there, and the drive to the museum has a note about stopping for your breakfast, but there are no lunch or dinner events.

Q: Do the kids have something planned for every weekday this week?
Tool use: Get this week’s events
A: Yep, they have X on Monday, Y on Tuesday, …

I could get used to this…

Jul 6, 2024

Thing I did with AI today:

Uploaded a photo of the calendar for this school year
Asked for a list of all the events
Requested a few rephrasings
Asked for a copy in ICS format
Imported it into my calendar

Apr 24, 2024

Does anyone else see ML-generated ads this specific?

An ad that looks ML-generated, saying only "join in tuple calculus" with a media play button and a photo of an individual with unknown relation to tuple calculus.

Apr 19, 2024

My long-awaited!

Screenshot of a macOS alert that says "Soulver 3 for iPhone is now available"

Mar 24, 2024

Congratulations, Obsidian, on graduating to my dock!

I installed it for the first-class iCloud sync, but inline PDF display and the spaced repetition plugin have made it essential.

Mar 7, 2024

Baa baa, terse sheep, have you any wool?

Yes.

Mar 1, 2024

I think that cross traffic should stop

Feb 27, 2024

1,794 pages in Logseq, with 279 embedded images and 156 annotated and deep-linked PDFs… but Obsidian is so fast.

Feb 25, 2024

My 3yos call a table of contents the “picking page” because you use it to pick a page to read 💡

Feb 20, 2024

If my 3yo sees an apartment building and asks, “Why are all those houses stuck together?” then someone told them the joke, right? Is that just a normal human observation?

Feb 20, 2024

“Outside-in” is when you make it itself

Feb 15, 2024

I think about that comic book movie where this magic labyrinthian map appears in the floor for like 30 seconds and everyone memorizes it for the chase scene later, but I have to keep the tab open that tells me the order of arguments to the “map” function.

Feb 12, 2024

Is there macOS app that gives me a global hotkey to talk to ChatGPT in a Spotlight-like popup?

Feb 7, 2024

Tomorrow will be a big day, just like yesterday and today, and all too many days lately.

Feb 2, 2024

Thanks to the power of View Source, I’ve embedded WebPPL on a page of my own site!

Just a simple (but perhaps more evocative than usual) intro to the language for now: http://alltom.com/pages/webppl-intro/

Snippet of the article with some code example and a wiggly graph, presumably generated by the code

Feb 2, 2024

What native macOS (textual) code editors still have some wood behind them? Sublime Text? Nova? TextMate? BBEdit? I’ll try anything if someone can vouch for its working effortlessly on Sonoma.

Jan 30, 2024

If you’re wondering about day 1 using HEY Calendar.

The first event I added recurs three days a week, which is not an option.

The second event I added overlapped with the first in a way that glitched the renderer into showing it with the wrong time and duration.

😬 Gonna wait for V2.

Jan 25, 2024

In the near future, upgrades for Mathematica will be available only as part of a subscription to your license, as we will no longer offer upgrade-only purchases.

Jan 18, 2024

Today’s failed Mathematica experiment: ordering fruit by fiber per unit volume.

Use a chat cell to get a list of fruit? ✅
Convert to entities with Interpreter["Food"]? ✅
Get fiber content with EntityValue[#, "DietaryFiberContentPerServing"] / EntityValue[#, "DefaultServingSizeVolume"]? ❌

List of fruits with corresponding fiber per unit volume, except many of the values are missing

Jan 12, 2024

I read Stephen’s whole article on what’s new in Mathematica 14, as usual. Version 13 had so many new LLM features that I had to upgrade, but the only features in 14 that I think will affect my life are DateObject and Quantity getting 100–1,000x faster. Awesome, but I’ll probably skip this one.

Jan 11, 2024

The “Cognition” in Probabilistic Models of Cognition 📚 is the hardest part to get across when I recommend this book. Because the book isn’t “Bayes works, yawn.” It’s so much more interesting if you, like me, exist primarily in ML circles that focus on curve-fitting:

What could be going on in our heads when we can’t tell that the two grid squares in that optical illusion are the same color? (Here’s an idea)
Can a computer model explain what makes it difficult for people to tell whether some stacks of blocks will fall? (Seems like it)
People seem to communicate by picking words that maximize the likelihood of a listener understanding them, according to our internal models of those listeners, which includes their attempt to guess what we would say to maximize being understood, which includes their attempt to guess… anyway, do we get sensible results of computers model listeners modeling speakers modeling listeners…? (Yes!)
Did you know that you learn more about world state transitions from observations if you assume that the actor is rational? (It’s true, and this chapter is the most mind-blowing for me)

There are tiny, self-contained, editable code examples to demonstrate almost every point, and they run in-browser! I love this book.

Optical illusion of a checkerboard pattern that's half in shadow, where the apparent color of a light square in shadow differs from that of a dark square outside the shadow, when their actual colors are actually equivalent

Jan 11, 2024

I’ve been re-reading Probabilistic Models of Cognition 📚 for probably the entire decade that it’s existed. Every time, I notice bits that have been rewritten or added, and notice that I understand just a little bit more. And yesterday, I understood everything cover-to-cover for the first time! 🙌🏼