Sundar @digital_carver@qoto.org

Free, light, autumn leaf
Sans home, drifts around, detached
Brittle, dry, fading.

#haiku #poem #poetry

@actuallyautistic

It makes a big difference to go from

“I feel like I wanna cry for no reason at all and I don’t know what to do about it” (- helplessness)

To

“I feel like I wanna cry for no reason at all. Why could it be?
It feels like I’m overwhelmed. By what?
Two days of constant masking in a strange new place is probably it (even if the people around were lovely). What can I do about it?
Quiet time, rest, giving myself permission to disengage from social obligations for a while.” (- making sense of it, understanding myself, and self-care)

It’s taken many years to arrive here, but I’m happy to notice that I’ve made progress.

#ActuallyAutistic #masking #selfcare

@hankg
Definitely agree with the recommendation to use AGPL.
In this case, though, it appears to have been a misunderstanding on Ghost’s side. There’s a further thread from Substack that explains it, and the screenshots also verify what they say - it’s Ghost-compatible code, not Ghost-originated code, and the JS is also fetched from the very common jsdelivr CDN, which both Ghost and Substack are using.

@theautisticcoach
Ha. I’m in India and grew up here - personal space is as much of a mythical concept to me as leprechauns and unicorns.

After playing with #ChatGPT for a bit, I’m still impressed by what it’s capable of achieving (sometimes), but I can see that it still has an ELIZA side to it - a tendency to go on random tangents,
to repeat answers,
to ignore chunks of the question and make up its own unique interpretation of it.

[ChatGPT’s full response below:]

There is no single secret to making Julia code fast, as the performance of Julia code can depend on a number of factors. However, there are a few general strategies that can help to optimize the performance of Julia code and make it run faster, such as:

• Choosing the right data types and structures: Julia is a dynamically-typed language, which means that the type of a variable can change at runtime. This can make it difficult to optimize the performance of your code, because the compiler cannot always determine the best way to represent and manipulate your data. To make your code run faster, you should choose the appropriate data types and structures for your data, based on the operations you want to perform and the performance characteristics of the different types.
• Avoiding unnecessary computations: Inefficient code often contains unnecessary computations, such as calculations that are performed multiple times or operations that do not affect the result of the program. To make your code run faster, you should avoid performing unnecessary computations, and try to structure your code in a way that minimizes the amount of work that the computer has to do.
• Using built-in functions and libraries: Julia has a rich set of built-in functions and libraries that can help you perform common tasks efficiently. Rather than implementing your own algorithms or functions, you should use the built-in functions and libraries whenever possible, as they are often highly optimized and can save you a lot of time and effort.
• Exploiting parallelism and vectorization: Julia is designed to support parallel computing and vectorization, which can help you to make your code run faster by utilizing multiple cores or processors. To make the most of these features, you should try to structure your code in a way that allows it to be executed in parallel or vectorized, and use the appropriate techniques and tools to parallelize or vectorize your code.

I asked #ChatGPT “What is the secret to make Julia code fast?” (just to see if it picks up anything from Jakob Nissen’s excellent guide https://viralinstruction.com/posts/optimise/ or the many other #julialang optimization guides online).

The answer turned out to be good example of the model’s ability to be subtly misleading while not being entirely wrong.

(Thread, with ChatGPT’s reply as the next post.)

Todo.txt with the Vim plugin gives me most of these except for the first two.

+Projects don’t really do the job for me with regard to subtasks, not nearly flexible enough.

Someone recommended TaskWarrior, but it looks like that doesn’t have subtasks either?

Have been thinking about extending the Todo.txt format in some way to support subtasks, not sure yet what the best way to go about it is. Sometimes I also want the subtasks to be strictly ordered (“show me only the next available subtask in order, not all of them”), sometimes they’re fine unordered. Hmmm…

#todotxt #TaskManagement #Projects

Thinking out loud:

What I want from a todo system are

• ability to break down a task at any point into subtasks (and automatically track completion)
• dependence between tasks i.e. ability to say Task X depends on Task N which depends on Tasks C and D
• easy keyboard manipulation, no mouse dependence
• plaintext or near-plaintext storage
• priorities
• contexts
• being FOSS and local
• (nice to haves:) tags, recurring tasks

#todo #TodoApps #TaskManagement #AppRecs

@voidabyss
That’s exactly what gives it the feel of the early Internet. There’s a sense of serendipity to it, and it actually lets you feel how wide and diverse the world is!

@ashwinvis

None that were at an “omg this changes everything” level (though the Sixels one could be that when the project is more mature).

But I liked David Kunz’s talk a lot, and the #Lua primer was pretty useful.

“The philosophy of vim” was nice in a nostalgic way, about the way computing starts to feel different when using #FOSS tools, and gives a feel of ownership over your software.

(I watched from David Kunz’s talk upto the Sixels one.)