2w ago

this is not ragebait rule

i hope this doesn't cause too much hate. i just wanna know what u people and creatures think <3

You're viewing a single thread.

75 comments

LMs give the appearance of understanding, but as soon as you try to use them for anything that you actually are knowledgable in, the facade crumbles.
Even for repetitive tasks, you have to do a lot of manual checking to ensure they did not start hallucinating half way through.
- I haven't really used AIs myself, however one of my brothers loves AI for boilerplate code which he of course looks over afterwards. If it saves time and you only have to do some minor editing then that seems like a win to me. Probably shouldn't be used like this in any non-hobby project by people who aren't adept at coding however
  
  I'm a programmer as well. When ChatGPT & Co initially came out, I was pretty excited tbh and attempted to integrate it into my workflow, which kinda worked-ish? But was also a lot of me being amazed by the novelty, and forgiving of the shortcomings.
  Did not take me long to phase them out again though. (And no, it's not the models I used; I have tried again now and then with the new, supposedly perfect-for-programming models, same results). The only edgecase where they are generally useful (to me at least) are simple tasks that I have some general knowledge of (to double theck the LM's work) but not have any interest in learning anything further than I already know. Which does occur here and there, but rarely.
  For everything else programming-related, it's flat out shit.I do not beleive they are a time saver for even moderately difficult programs. Bu the time you've run around in enough circles, explaining "now, this does not do what you say it does", "that's the same wring answer you gave me two responses ago", "you have hallucinated that function", and found out the framework in use dropped that general structure in version 5, you may as well do it yourself, and actually learn how to do it at the same time.
  For work, I eventually found that it took me longer to describe the business logic (and do the above dance) than to just.... do the work. I also have more confidence in the code, and understand it completely.
  In terms of programming aids, a linter, formatter and LSP are, IMHO, a million times more useful than any LM.
  
  this matches my experience too. good IDEs or editors with LSP support allll the way.
  also wanna add that it's weird to me that we turn to LLMs to generate mountains of boilerplate instead of... y'know, fixing our damn tools in the first place (or using them correctly, or to their fullest) so that said boilerplate is unnecessary. abstractions have always been a thing. it seems so inefficient.
  
  Makes me feel warm around the heart to hear that it's not just me 🫠
  
  ikr, it makes the horrors just a little more bearable ✨
  
  I also 100% agree with you. My work has a developer productivity team that tries to make sure we have access to good tools, and those folks have been all over AI like flies on shit lately. I've started to feel a bit like a crazy Luddite because I do not feel like Copilot increases my productivity. I'm spending like 90% of my time reading docs, debugging and exploring fucked up edge cases, or staring off into space while contemplating if I'm about to introduce some godawful race condition between two disparate systems running in kubernetes or something. Senior developers usually do shit that would take hours to properly summarize for a language model.
  And yeah, if I have to write a shitload boilerplate then I'm writing bad code and probably need to add or fix abstraction. Worst case, there's always vim macros or a quick shell oneliner to generate that shit. The barrier to progress is useful because it warns me that I'm being a dummy. I don't want to get rid of that when the only benefit is that I get to context switch between code review mode and system synthesis mode.
  
  Yeah, with seniors it's even more clear how little LMs can help.
  I feel you on the AI tools being pushed thing. My company is too small to have a dedicated team for something like that, buuuut... As of last week, we're wasting resources on an internal server hosting Deepseek on absurd hardware. Like, far more capable than our prod server.
  Oh, an we pride ourselves on being soooo environmentally friendly 😊🎉
  
  for even moderately difficult programs.
  My brother uses it to generate templates and basic structs and functions, not to generate novel code. That's probably the difference here. I believe it's integrated into his text editor as well? It's the one github offers
  Edit: Probably wouldn't be useful if it wasn't integrated into the editor and therefore the generation being just a click away or some sort of autofill. Actually writing a prompt does sound tedious
- you're right, it doesn't do classification perfectly every time. but it drills down on the amount of human labour required to classify a large set of data.
  about the knowledge: it really comes down to which model you are talking to. "generalist" models like GPT4o or claude 3.5 sonnet have been trained to know many things somewhat, but no single thing perfectly.
  currently companies seem to train largely on IT-related things. these models are great at helping me program, but they are terrible at specifically writing GDScript (a niche game-programming language) since they forget all the methods and components the language has.
  
  Even with LMs supposedly specialising in the areas that I am knowledgable (but by no means an expert) in, it's the same. Drill down even slightly beyond surface-level, and it's either plain wrong, or halucinated when not immediately disprovable.
  And why wouldn't it be? These things do not possess knowledge, they possess the ability to generate texts about things we'd like them to be knowledgable in, and that is a crucial difference.
- I've heard this argument so many fucking times and i hate genai but there's no practical difference between understanding and having the appearance of such, that is just a human construct that we use to try to feel artificially superior ffs
  
  No. I am not saying that to put man and machine in two boxes. I am saying that because it is a huge difference, and yes, a practical one.
  An LLM can talk about a topic for however long you wish, but it does not know what it is talking about, it has no understanding or concept of the topic. And that shines through the instance you hit a spot where training data was lacking and it starts hallucinating. LLMs have "read" an unimaginable amount of texts on computer science, and yet as soon as I ask something that is niche, it spouts bullshit. Not it's fault, it's not lying; it's just doing what it always does, putting statistically likely token after statistically liken token, only in this case, the training data was insufficient.
  But it does not understand or know that either; it just keeps talking. I go "that is absolutely not right, remember that <....> is <...,>" and whether or not what I said was true, it will go "Yes, you are right! I see now,
  <continues to hallucinate>
  ".
  There's no ghost in the machine. Just fancy text prediction.

75 comments