Does anyone know, or can anyone guess, the business case for predictive text? On phone apps, it is often incredibly difficult to turn off. Why is that, do you think? (The examples I have recent experience with are Facebook and Outlook mobile apps.)

I would have thought that, for AI training purposes, they would want humans typing things and not just regurgitating canned responses. But apparently not?

cross-posted from: https://lemmy.pe1uca.dev/post/1137911

I need to help auditing a project from another team.
I got the pointers on what's expected to be checked, but I don't have like templates for documents for what's expected from an audit report which also means I'm not sure what's the usual process to conduct an internal audit.
I mean I might as well read the whole repo, but maybe that's too much?

Any help or pointers on what I need to investigate to get started would be great!

Hello everyone, I have an idea to make a map with fog of war, when you walk you explore new areas and points of interest but you can't see unexplored areas. I'm not sure if it's a good idea, what is your opinion?

One thing that pretty consistently drops me out of the flow state is having to dig through documentation for whatever I'm trying to use, or even worse having to dig through its source code because the documentation is either nonexistent or eg. plain wrong

Raphael Kabo's personal website and writing on programming, poetry, and academia.

Qt 6.7 is out with lots of large and small improvements for all of us who like to have fun when building modern applications and user experiences. Several additions are released as technology previews, and we are looking forward to your feedback so that we can get everything ready for the next LTS release!

I have a script that duplicates a Word doc template and renames each using a csv file with a list of names. What would be the equivalent code if instead of a csv file I use a text file?

Import-csv ‘.\individuals2.csv’ | foreach-object {
	$newname = ‘2 ‘ + $_.name + '.docx’
	Copy-item '.\template.docx' $newname
}

cross-posted from: https://feddit.nl/post/12252747

This project was interesting. Recently, I've been digging into the functional programming paradigm. This is one of my first tries at it. I've been doing OOP until recently, but this project really was impressive to me. The whole implementation took about nine hours. Functional programming is much less convoluted. I spent more time programming than deciding on a good name for a certain identifier.

Not only is functional programming more efficient, but I can also see that it's much less tedious to write automated tests for. I only have to take care of the local scope of the function I am writing a test for; there is no need to deal with the parent's inherited mess or even any parent's mere state. I just have to write the test for the function.

I have scraped the Cambridge Dictionary to collect the data.

The project is licensed under MIT at:

https://github.com/eeriemyxi/novi

https://git.envs.net/myxi/novi

cross-posted from: https://sopuli.xyz/post/10010650

Ran into this on HN and had to share it. I love esolangs with "surprising" source representations

Think of a similar scope of change to a large codebase you're familiar with, for frame of reference.

Hello! I'll try to explain what I'm looking for: I sometimes have to write simple web pages (not just text, also buttons and video players and so on), but I really really hate writing html code. What I'm used to is QML, which I like a lot, because of the ease of placing objects exactly where I need using the anchors and the Layout objects. What I'm looking for is a language or something with a similar syntax, that can then be "built" to plain HTML/CSS/JS. Is there something like this? I know I can compile Qt/QML for webassembly, but I'm having huge amounts of problems, and also I'd like to have the possibility to have a plain HTML result, not necessary bind to the server side.

thanks in advance!!

cross-posted from: https://lemmy.ca/post/15730457

I've written a basic media player using Python, PyGTK, and GStreamer. However, I've found a bug that I'm having trouble finding a fix to.

In this program, opening a video launches a second window, in which the video is played back. If I close said window, however, the control window freezes and I get the following error:

gst-resource-error-quark: Output window was closed (3) ../sys/xvimage/xvimagesink.c(586): gst_xv_image_sink_handle_xevents (): /GstPlayBin:player/GstPlaySink:playsink/GstBin:vbin/GstXvImageSink:xvimagesink0

The source code can be found here.

Does anybody have any idea how to fix this? Or is this perhaps a bug in one of the libraries?

Subverting Betteridge's law of headlines. Yes.

Not mine.

"Part 1" is this, it's also linked to in the body.

I really wonder what happened:

Update (21 August 2023): I did continue my investigation, but I have decided not to publish the results. Please do not continue to email me about this.

I'm digging into the world of #FOSS #opensource and would like to help with existing projects. My programming chops are not sharp yet, but I'm a detail-oriented communicator who knows a bit about user testing.

How do I find projects on GitHub, GitLab, or other sites that need this kind of help? The machines I would be testing on are a potato desktop running Pop_OS Linux and an Android phone. Thanks in advance!

Edit 2024-01-26: I ended up feature creeping it a bit. It can now be used as a less input filter, and asciinema-esque recording playback.

Original post:

A less bad name TBD.

This is a little program I made to convert script captures into properly laid out text. A lot of the behaviour still isn't quite right, but I'm pretty happy with it as a proof-of-concept.

So. I was working with this code:

public function front(?string $sortBy,
        ?string $time,
        ?string $type,
        ?string $filter,
        string $federation,
        Request $request): Response
    {
        $user = $this->getUser();

        if (!$user)
        {
            $filter = 'all';
        }

        $criteria = new EntryPageView($this->getPageNb($request));
        $criteria->showSortOption($criteria->resolveSort($sortBy))    

... and so on; the function continues. VSCode told me there was a syntax error on the close brace on the if statement. I stared at it for a while, then pasted the code into GPT (not Copilot). Here's the conversation we had about it:

Me

What's the syntax error here?

(and I pasted the code)

GPT

The syntax error in your PHP function public function front seems to be due to the incorrect placement of the closing curly brace for the if statement. It appears that the if statement is not properly closed before the $criteria initialization begins. The corrected code should look like this:

public function front(?string $sortBy, ?string $time, ?string $type, ?string $filter, string $federation, Request $request): Response
{
    $user = $this->getUser();

    if (!$user) {
        $filter = 'all';
    } // Closing brace for the if statement

    $criteria = new EntryPageView($this->getPageNb($request));
    $criteria->showSortOption($criteria->resolveSort($sortBy));
    // ... rest of your function code ...
}

Ensure that each statement and block is properly closed and followed correctly by the next statement. This corrected structure should resolve the syntax error you are encountering.

Me

I don't get it. I put a closing curly brace right after the statement in mine... what am I missing?

GPT

I apologize for the confusion. Upon re-examining your code, it seems the placement of the curly brace is correct. If you're still encountering a syntax error, it may not be related to the if statement structure.

Let's look at other possible issues:

... and so on. Pasting GPT's recommended if-statement block, including the curly brace that was already there, fixed the error. I have since re-pasted the same thing I initially gave to GPT to VSCode, and it all works now, and asking the exact same question of GPT again now leads to random guesses which have nothing to do with the cursed curly brace that was previously causing problems for both VSCode and GPT.

I have given up and moved on at this point, content to say vaguely that maybe the unusual brace style, or pasting the incomplete function without semicolon or final close brace, managed to coincidentally confuse GPT on exactly the same line where VSCode had gotten confused for unexplained reasons. But the whole thing still has this Twilight-Zone oddness to me.

Text description (for those with screenreaders):

A portion of a prime number checker written in the Rust programming language, where the first few lines are written correctly including the first if statement in the program. However, the following if statements are written using Python syntax instead of Rust, as the author slipped back into his native tongue.

EDIT: Thanks y'all! I got this working by installing mutt and configuring it with my Gmail info. Please note the warning from u/jherazob below--if this were something mission critical I would not want to rely on this solution.

================

Noob question incoming, thanks in advance for any help with this!

I have a specific use case in which I want to send an automated email or text to myself once a day (the message is different each time--otherwise I would just set an alarm, lol!). I'm running Pop_OS on an old desktop computer. Where I'm stuck is getting an email to successfully send from the command line. I'm looking for easy-to-follow instructions that would help me do that, and none of the articles or videos I've come across thus far have helped.

I'm aware of Twilio and other services that send SMS messages, but I'm looking for something free. Especially since I only need to text one person (myself), and infrequently at that.

Below is my attempt to send an email with the telnet command. Nothing ever came through...

XXXXXXXX@pop-os:~$ telnet localhost smtp
Trying ::1...
Connected to localhost.
Escape character is '^]'.
220 pop-os ESMTP Exim 4.95 Ubuntu Sun, 07 Jan 2024 15:12:28 -0500
HELO gmail.com
250 pop-os Hello localhost [::1]
mail from: [email protected]
250 OK
rcpt to: [email protected]
250 Accepted
data
354 Enter message, ending with "." on a line by itself
Subject: Test
Body: Is this working?
.
250 OK id=1rMZW4-0002dj-Uy
quit

cross-posted from: https://programming.dev/post/8121843

~n (@[email protected]) writes:

This is fine...

"We observed that participants who had access to the AI assistant were more likely to introduce security vulnerabilities for the majority of programming tasks, yet were also more likely to rate their insecure answers as secure compared to those in our control group."

[Do Users Write More Insecure Code with AI Assistants?](https://arxiv.org/abs/2211.03622?