digital_carver - Network

Jan 13, 2024, 18:25

I'm someone who argued fifteen years ago against Linux fanatics who wanted to pretend #Linux was a viable replacement for the average user for #Windows. As much of a #FOSS enthusiast as I am, that simple wasn't true at the time - Windows was a much smoother experience in general than Linux.

Today though, I can confidently recommend a major Linux distro and know that they'll have as smooth an experience as they would on Windows. Not (just) because Linux has improved by leaps and bounds, but also because Microsoft seem to be doing a great job driving Windows to the ground.

Jan 13, 2024, 18:19

Windows really has gone downhill!

While my laptop is away being repaired, I got a rental laptop. I asked for a #windows machine just to if I'm missing out on some latest flashy advances in proprietary land, having been on #Linux for many years now.

And I can't believe this is the world's primary OS! It's a buggy, unintuitive mess (and this is coming from someone who used Windows for 10+ years) where the only "advance" seems to have been in being ever more intrusive and taking more and more control away from the user.

Jan 13, 2024, 11:05

Real answer: because sex takes over everything, while Nazis only wish they could. People come up with all these complicated hypotheses about puritanism and shriveled old men controlling everything not wanting anyone to have fun - if you think those types of reasons would overrule people's greed for more traffic and more money, you have too rosy a view of humanity.

The simple truth is that once you allow sexual content on a platform, the majority of the content you'll be serving henceforth will be sexual. Advertisers don't like that, most parents don't want that, and your legal team and your PR/marketing team aren't gonna like the thorny and potentially brand-ruining issues this is going to bring in.

Sep 23, 2023, 17:03

The One Piece live action on Netflix has a Tamil dub, and it actually isn't bad!

Usually in Tamil dubs, they seem to take out all the flavour of the dialogue, making it very basic. So I was expecting to be disappointed and move back to English when I changed the Audio language, but they surprised me!

#tamil #onepiece #anime #netflix

Dec 22, 2022, 17:57

an example of the plausible-sounding bullshit (about the Venpa rhyming scheme in #Tamil). this one's not in the "abcb" scheme, there's no "third" or "fourth" lines, and I think this is not even a Venpa:

#ChatGPT #LLM

Dec 22, 2022, 17:56

#ChatGPT is a great school-essay generator!

It always sounds confident and formal - regardless of whether its showing deep understanding and insight, or spouting plausible-sounding bullshit vaguely related to the question.

Exactly what students do!

Dec 14, 2022, 20:00

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

#haiku #poem #poetry

Dec 14, 2022, 15:33

@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

Dec 11, 2022, 15:08

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.

Dec 11, 2022, 14:51

Content warning: ChatGPT stuff

Zooming out to generalize, it seems likely that this'll be a significant issue with ChatGPT/other LLM responses - mistakes like this are subtle and insidious, and could easily pass muster at a first glance. Especially if you don't know the answer already, which will be the case when people actually start using it beyond this trial.

Information about things that are already popular and has a lot of text on the Internet - pre-established languages, technologies, the currently dominant cultures, ideologies, etc. - will be well known to ChatGPT, and could be commingled in subtle ways with newer upcoming ones, and presented as part of that newer entity, perpetuating those old influences.

This type of misinformation will be insidious, and can easily fly under the radar in a lot of situations.

#AIBias #AIEthics #ChatGPT #LLM #LargeLanguageModels

Dec 11, 2022, 14:38

Content warning: ChatGPT stuff

tl;dr: it seems likely ChatGPT took advice meant for Python or MATLAB, and substituted Julia's name in their place because it considers them "close enough".

1 isn't wrong, but makes no mention of type stability, which is at least as important as its (more generic, applicable many languages) suggestion.

2 is also generic advice that's good to have, but isn't #JuliaLang specific (but I consider this one a #ChatGPT success)

3 rates as kinda okayish advice. One could argue that for a beginner, the base functions offer a solid place to start, if we assume they're gonna write badly optimized code (but then teaching them how not to do that - as the prompt asked - is a better way to solve that). But since this is Julia, it's not uncommon that simple custom code you write beats the obvious ways using built-ins. So I'd consider this potentially misleading.

4 is likely the smoking gun here - the repeated mentions of vectorization and asking to use techniques to "vectorize your code" seems to suggest that this whole thing was taken from guides written for Python or MATLAB, which are at this point more numerous than those for Julia, and then the Language Model substituted Julia in the language name's place because it considers them similar. (A previous answer said "there are a number of programming languages that are commonly used for numerical and scientific computing, including Python, Julia, MATLAB, R, and others" - so it knows they're in the same category.)

Dec 11, 2022, 14:22

Content warning: ChatGPT stuff

[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.

Dec 11, 2022, 14:21

Content warning: ChatGPT stuff

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.)

Dec 10, 2022, 17:58

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

Dec 10, 2022, 17:52

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

Dec 03, 2022, 13:13

It's concerning how much of my self-talk involves telling myself:
"We'll catch up on sleep later, I promise, but let's pretend for now that we're well-rested and alert and not a grumpy sleep deprived husk at all."

#sleep #SleepDeprived

Dec 03, 2022, 12:15

Mmm, yes, let's keep procrastinating on getting ready for this social engagement with strangers.
That'll somehow make things easier, yep.

#introvert #meetingnewpeople #procrastination

Dec 03, 2022, 05:17

Content warning: bird site talk

I've probably visited the bird site more times in the past couple weeks than I ever have in the past.

I made an account in the very early days, didn't see the point of the site, and rarely used it. When I finally did want a microblogging network, #Mastodon and #Qoto were ready and more appealing.

But now I keep seeing posts about how so much is changing there and how X happened and Y is about to happen, and it makes me want to check it out and see what it's actually like.

#Twitter #StreisandEffect

Dec 02, 2022, 15:05

Have seen fellow #ActuallyAutistic people talk about the times they go non-verbal, where talking feels very difficult/impossible.

Does that usually go in the other direction too, i.e. listening to people talk? For me it often does - when I go non -verbal, I also can't take in information in verbal form, whatever the source. I can't listen to podcasts or watch YouTube videos, or even listen to music that has lyrics.

I'm experiencing it right now, and even the lightest of podcasts, a comedy podcast that I enjoy and have even already listened to, feels overwhelming. My brain's gone "we're full right now, shop's closed, please come back later".

Nov 29, 2022, 05:44

Logseq looks pretty good for personal wiki/knowledge management/notes-taking stuff. I like a lot of things about it.

But I'm resisting the usual urge to go all-in once I find something good, to transfer everything from my previous systems to this asap.

Going slow will let me find out what the weak spots of this particular ecosystem are, before I invest too much into it. Then, I can figure what use-cases are best fit for it, and what should remain in other systems.

#logseq #personalwiki #vimwiki #zotero #recfiles