The reason I get so annoyed about people pitching LLMs as a way to 'democratise programming' or as end-user programming tools is that they solve the wrong problem.
The hard part of programming is not writing code. It's unambiguously expressing your problem and desired solution. Imagine if LLMs were perfect programmers. All you have to do is write a requirements document and they turn it into a working program. Amazing, right? Well, not if you've ever seen what most people write in a requirements document or seen the output when a team of good programmers works from a requirements document.
The most popular end-user programming language in the world (and, by extension, the most popular programming language), with over a billion users, is the Calc language that is embedded in Excel. It is not popular because it's a good language. Calc is a terrible programming language by pretty much any metric. It's popular because Excel (which is also a terrible spreadsheet, but that's a different rant) is basically a visual debugger and a reactive programming environment. Every temporary value in an Excel program is inspectable and it's trivial to write additional debug expressions that are automatically updated when the values that they're observing change.
Much as I detest it as a spreadsheet, Excel is probably the best debugger that I have ever used, including Lisp and Smalltalk.
The thing that makes end-user programming easy in Excel is not that it's easy to write code, it's that it's easy to see what the code is doing and understand why it's doing the wrong thing. If you replace this with an LLM that generates Python, and the Python program is wrong, how does a normal non-Python-programming human debug it? They try asking the LLM, but it doesn't actually understand the Python so it will often send them down odd rabbit holes. In contrast, every intermediate step in an Excel / Calc program is visible. Every single intermediate value is introspectable. Adding extra sanity checks (such as 'does money leaving the account equal the money paid to suppliers?') is trivial.
If you want to democratise programming, build better debuggers, don't build tools that rapidly generate code that's hard to debug.
The word "idea" sounds like "idiate". I'm reminded of this a lot now.
WordNet (r) 3.0 (2006) (wn)
ideate
v 1: form a mental image of something that is not present or
that is not the case; "Can you conceive of him as the
president?" [syn: imagine, conceive of, ideate,
envisage]
This shouldn't be necessary.
https://arstechnica.com/ai/2025/03/cloudflare-turns-ai-against-itself-with-endless-maze-of-irrelevant-facts/
This is terrible stuff. Have your projects been affected?
https://thelibre.news/foss-infrastructure-is-under-attack-by-ai-companies/
#ai #enshittification #foss
The college #SmashBros club I'm in got the first clip! https://youtu.be/HH1lJgM7HFw
I have an idea. What if in #Mastodon, the way you quote-post (a la "quote tweet") is by replying to someone then boosting your own message. Works about the same, but requires a click to see the post being replied to.
GIMP 3.0 is released, check it out!
https://testing.gimp.org/release-notes/gimp-3.0.html
A huge THANK YOU to everyone who contributed in any way - from testing and submitting bug reports through to designing, coding, fixing, packaging, testing some more, translating, documenting, hosting, administration, so many people, so much work, so much to be thankful for!
Welcome to GIMP 3.0!
For parents with kids who are putting out leprechaun traps today: a 3d printed leprechaun hat takes less than 30 mins to print, and is a great thing to leave in their trap after you take the bait.
@Alexandrad1 @anderseknert @quintessence The mod is out of line, using grandstanding language that tries to portray the user as a bad actor. “I’m going to step in”, “you have chosen this action”, “had seemed kind”.
There’s a whole bunch of language about how the mod was almost surprised the account didn’t have a history of misinformation. Deleting a (popular and legit) post about a sensitive topic and then going dark for 18 hours is not really a proper course of action in my book.
They don't seem to be doing it on bad faith, but I do think they should've asked for more info before deleting your post.
I don't know how Mastodon's backend works, but maybe moderators could have an option that, instead of deleting a post, puts it on hold until the fact-checking process is done, including giving the post owner the chance to comment?
And if they see that it was flagged wrongly, they just enable the post to be seen by everybody again.
Hello there!
I boost a lot of posts, but I have a few things to say every now and then.
I am largely fine with boosting posts from people I disagree with even on significant, dividing issues. I usually don't, however, if they actively advocate for these ideas... so it goes :/
#Christian #coding #HaikuOS #Linux #privacy #FOSS #Fediverse #SmashBros #SSBU #LegendOfZelda
#fedi22
Note: social.librem.one doesn't support DMs