ChatGPT Is Still a Bullshit Machine

Comments

• BallShapedMan@lemmy.world ⁨2⁩ ⁨days⁩ ago

  A lady I can’t stand who is condescending to everyone like the worst version of a grade school teacher resigned recently so she can market her GPT “models” full time.

  Last week she used “Salem” her GPT prompt BS to read through a detailed document my department put together to see what was missing. She shared her screen with obvious gpt slop and started pointing out all the things we didn’t answer. The lady on my team who put the very specific and detailed document together just started reading the answers right from the document that showed it was clearly and precisely answered. The lady I can’t stand stopped sharing her screen and quit talking.

  The moral of the story, gpt did me a solid by convincing this person who’s clearly never heard of the Dunning Kruger effect that she needs to quit her well paying job and stop being a pain in my ass.

  Thank you GPT!! Best thing is ever done for me.

  source

  • jubilationtcornpone@sh.itjust.works ⁨2⁩ ⁨days⁩ ago

    Holy shit. I think you just found a valid use for LLM’s. OpenAI valuation intensifies

    source
• kescusay@lemmy.world ⁨2⁩ ⁨days⁩ ago

  Software developer, here. (No, not a “vibe coder.” I actually know how to read and write my own code and what it does.)

  Just had the opportunity to test GPT 5 as a coding assistant in Copilot for VS Code, which in my opinion is the only legitimately useful purpose for LLMs. (No, not to write everything for me, just to do some of the more tedious tasks faster.) The IDE itself can help keep them in line, because it detects when they screw up. Which is all the time, due to their nature. Even recent and relatively “good” models like Sonnet need constant babysitting.

  GPT 5 failed spectacularly. So badly, in fact, that I’m glad I only set it to analysis tasks and not to any write tasks. I will not be using it for anything else any time soon.

  source

  • Pechente@feddit.org ⁨2⁩ ⁨days⁩ ago

    Yeah right? I tried it yesterday to build a simple form for me. Told it to look at the structure of other forms for reference which it did and somehow it used NONE of the UI components and helpers from the other forms. It was bafflingly bad

    source

    • errer@lemmy.world ⁨2⁩ ⁨days⁩ ago

      Despite the “official” coding score for GPT5 being higher, Claude sonnet still seems to blow it out of the water. That seems to suggest they are training to the test and the test must not be a very good test. Or they are lying.

      source

      • -> View More Comments
  • LiamMayfair@lemmy.sdf.org ⁨2⁩ ⁨days⁩ ago

    I tried GPT-5 to write some code the other day and was quite unimpressed with how lazy it is. For every single thing, it needed nudging. I’m going back to Sonnet and Gemini. And even so, you’re right. As it stands, LLMs are useful at refactoring and writing boilerplate and repetitive code, which does save time. But they’re definitely shit at actually solving non-trivial problems in code and designing and planning implementation at a high level.

    They’re basically a better IntelliSense and automated refactoring tool, but I wouldn’t trust them with proper software engineering tasks. All this vibe coding and especially agentic development bullshit people (mainly uneducated users and the AI vendors themselves) are shilling these days, I’m going nowhere near around.

    I work in a professional software development team in a business that is pushing the AI coding stuff really hard. So many of my coworkers use agentic development tools routinely now to do most (if not all) of their work for them. And guess what, every other PR that goes in, random features that had been built and working are removed entirely, so then we have to do extra work to literally build things again that had been ripped out by one of these AI agents. smh

    source

    • MagicShel@lemmy.zip ⁨2⁩ ⁨days⁩ ago

      In a similar situation. I’m even an AI proponent. I think it’s a great tool when used properly. I’ve had great success solving basically trivial problems with small scripts. And code review is helpful. Code complete is helpful. It makes me faster, but you have to know when and how to leverage it.

      Even on tasks it isn’t good at, it often helps me frame my own thoughts. It can identify issues better than it can fix them. So if I say here is the current architecture, what is the best way to implement <feature> and explain why, it will give a plan. It may not be a great plan, but as it explains it, I can easily identify the stuff it has wrong. Sometimes it’s close to a workable plan. Other times it’s not. Other times it will confidently lead you down a rabbit hole. That’s the real time waster.

      “Why won’t the context load for this unit test?”

      You’re missing this annotation.

      “Yeah that didn’t do it. What else.”

      You need this plugin.

      “Yeah it’s already there.”

      You need this other annotation.

      “Okay that got a different error message.”

      You need another annotation

      “That didn’t work either. You sent actually know what the problem is do you?”

      Sad computer beeps.

      To just take the output and run with it is inviting disaster. It’ll bite you every time and the harder the code the worse it performs.

      source

      • -> View More Comments
  • Passerby6497@lemmy.world ⁨2⁩ ⁨days⁩ ago

    Yeah, LLMs are decent with coding tasks if you know what you’re doing and can properly guide it (and check it’s work!), but fuck if they don’t take a lot of effort to reign in. I will say they’re pretty damned good at debugging the shit I wrote. I’ve been working on an audit project for a few months and 4o/5 have helped me a good bit to find persistent errors in my execution logic that I just kept missing on rereads and debug runs.

    But new generation is painful. I had 5 generate a new function for me yesterday to do some issues recon and report generation, and I spent 20 minutes going back and forth with it dropping fields in the output repeatedly. Even on 5, it still struggles at times to not give you the same wrong answer more than once, or just waffles between wrong answers at times.

    source

    • webhead@lemmy.world ⁨2⁩ ⁨days⁩ ago

      Dude forgetting stuff has to be one the most frustrating parts of the entire process . Like forgetting a column in a database or just an entire piece of a function you just pasted in… Or trying to change things you never asked it to touch. So freaking annoying. I had standing instructions in it’s memory to not leave out pieces or modify things I didn’t ask for and will put that stuff in the prompt and it just does not care lol.

      I’ve used it a lot for coding because I’m not a real programmer (more a code hacker) and need to get things done for a website, but I know just enough to know it’s really stupid sometimes lol.

      source

      • -> View More Comments
    • Badabinski@kbin.earth ⁨2⁩ ⁨days⁩ ago

      Out of curiosity, do you feel that you would have been able to write that new function without an LLM in less time than you spent fighting GPT5?

      source

      • -> View More Comments
    • SpaceCadet@feddit.nl ⁨1⁩ ⁨day⁩ ago

      LLMs are decent with coding tasks if you know what you’re doing

      Only if the thing you are trying to do is commonly used and well documented, but in that case you could just read the documentation instead and learn a thing yourself, right?

      The other day I tried to get some instructions on how to do something specific in a rather obscure and rather opaquely documented cli tool that I need for work. I couldn’t quite make sense of the documentation, and I found the program’s behavior a bit erratic, so that’s why I turned to AI. It cheerfully and confidently told me (I’m paraphrasing): oh to do “this specific thing” you have to use the –something-specific switch, and then it gave some command line examples using that switch that looked like they made complete sense.

      So I thought: oh, did I overlook that switch? Could it be that easy? So I looked in the documentation and sure enough… the AI had been bullshitting me and that switch didn’t exist.

      Then there was the time when I asked it to generate an ARM template (again, poorly documented bullshit) to create some service in Azure with some specific parameters. It gave me something that looked like an ARM template, but sure as hell wasn’t a valid one. This one wasn’t completely useless though, at least I was able to cross reference with an existing template and with some trial-and-error, I was able to copy over some of the elements that I needed.

      source
  • takeda@lemmy.dbzer0.com ⁨1⁩ ⁨day⁩ ago

    Just had the opportunity to test GPT 5 as a coding assistant in Copilot for VS Code, which in my opinion is the only legitimately useful purpose for LLMs.

    The best use of LLM sadly is to use it on social media to spread disinformation. At that point making shit up isn’t a big but a feature.

    For coding I am still not sold on it. It seems to excel on tasks that were done millions of times like programming assignments at school, example/tutorial code, interview questions.

    For me while it helps in stone cases, I still have to go over the code and understand it and very often it introduces subtle bugs or I can write a more concise chose that fits my need. In those cases all the advantages it did are nullified, I suspect it might actually be slowing me down.

    It feels to me that LLM is a godsend to all the coders that previously copied code from stack overflow. It greatly streamlined the process and also included all code published on GitHub.

    source
  • jjjalljs@ttrpg.network ⁨2⁩ ⁨days⁩ ago

    Even when it gets it right, you have to then check it carefully. It feels like a net loss of speed most of the time. Reading and checking someone else’s code is harder than writing your own

    source

    • jj4211@lemmy.world ⁨2⁩ ⁨days⁩ ago

      On the code competition, I think it can do like 2 or 3 lines in particular scenarios. You have to have an instinct for “are the next three lines so blatantly obvious it is actually worth reading the suggestion, or just ignore it because I know it’s going to screw up without even looking”.

      Very very very rarely do I find prompt driven coding to be useful, like very boilerplate but also very tedious. Like “show user to specify these three parametets in this cli utility”, and poof, you got a reasonable argv handling pretty reliably.

      Rule of thumb is if a viable answer could be expected during an interview by a random junior code applicant, it’s worth giving the llm a shot. If it’s something that a junior developer could get right after learning on the job a bit, then forget it, the LLM will be useless.

      source
    • TheFogan@programming.dev ⁨2⁩ ⁨days⁩ ago

      have to agree on that, there’s the variation, it’s faster if you take it’s code verbatim, run it, and debug where there’s obvious problems… but then you are vulnerable to unobvious problems, when a hacky way of doing it is weak to certain edge cases… and no real way to do it.

      Reading it’s code, understanding it, finding the problems from the core, sounds as time consuming as writing the code.

      source
  • ThePowerOfGeek@lemmy.world ⁨2⁩ ⁨days⁩ ago

    I’m no longer even confident in modern LLMs to do stuff like convert a table schema or JSON document into a POCO. I tried this the other day with a field list from a table creation script. So it had to do was reformat the fields into a dumb C# model. Inexplicably it did fine except for omitting a random field in the middle of the list. Kinda shakes your confidence in LLMs for even the most basic programming tasks.

    source

    • kescusay@lemmy.world ⁨2⁩ ⁨days⁩ ago

      More and more, for tasks like that I simply will not use an LLM at all. I’ll use a nice, predictable, deterministic script. Weirdly, LLMs are pretty decent at writing those.

      source
  • Steve@startrek.website ⁨2⁩ ⁨days⁩ ago

    Not 5 minutes ago I asked gpt5 how to go back to gpt-4o.

    GPT5 was spitting out some strange bs for simple coding prompts that 4o handles well.

    source
  • brucethemoose@lemmy.world ⁨2⁩ ⁨days⁩ ago

    Have you given Qwen or GLM a shot?

    source

    • kescusay@lemmy.world ⁨2⁩ ⁨days⁩ ago

      Not yet. I’ll give them a shot if they promise never to say “you’re absolutely correct” or give me un-requested summaries about how awesome they are in the middle of an unfinished task.

      Actually, I have to give GPT 5 credit on one thing: It’s actually sort of paying attention to the copilot-instructions.md file, because I put this snippet in it: “You don’t celebrate half-finished features, and your summaries of what you’ve accomplished are not only rare, they’re never more than five sentences long. You just get straight to the point.” And - surprise, surprise - it has strictly followed that instruction.

      Fucks up everything else, though.

      source
• A_norny_mousse@feddit.org ⁨2⁩ ⁨days⁩ ago

  Sam Altman Is Still a Bullshit Machine

  source
• brucethemoose@lemmy.world ⁨2⁩ ⁨days⁩ ago

  ChatGPT Is Still a Bullshit Machine

  Just like Sam Altman.

  source
• galoisghost@aussie.zone ⁨2⁩ ⁨days⁩ ago

  Such a punchable face

  source

  • SugarCatDestroyer@lemmy.world ⁨2⁩ ⁨days⁩ ago

    There is a certain hypocrisy in this face…

    source
• vane@lemmy.world ⁨1⁩ ⁨day⁩ ago

  My kids will never be smarter than AI

  Sam Altman

  source
• Reverendender@sh.itjust.works ⁨2⁩ ⁨days⁩ ago

  I tried ChatGPT-5 for the first time this morning. I asked it to help me create an RSS list for some world news articles. For context I have never used RSS before. That was 90 minutes of my life I’ll never get back. Also, you can no longer choose any other models except for 5 and the 5-thinking model. Access to 4o is gone.

  source

  • PalmTreeIsBestTree@lemmy.world ⁨2⁩ ⁨days⁩ ago

    What did it do exactly? I haven’t kept up with AI because I’d rather not engage with it.

    source

    • Reverendender@sh.itjust.works ⁨1⁩ ⁨day⁩ ago

      It was consistently wrong about how to go about setting up a group feed on every single website it suggested. And I started out trying to work on my iPad, and it kept telling me where to find things, and it was wrong, and how to do something, and it was wrong, and it kept telling me supposed desktop instructions, even after I told it I was on an iPad, (an iPad is somehow different it claimed). So I went to the desktop and it was exactly the same as the iPad, as o knew it would be, meaning its instructions were just wrong. When I called it out and I asked it on its final recommendation to be absolutely sure that the process it was going to tell me was correct and up-to-date, and to read the website first before it gave me the information; it lied to me and said it was and that it would check first, and then didn’t do what it said it was going to do. Plus about 70% of RSS links it gave me were bad. It was just a really frustrating experience. Essentially going from version 4o to version 5 was a step backwards in AI evolution from what I can tell things,

      source
• some_guy@lemmy.sdf.org ⁨1⁩ ⁨day⁩ ago

  If you believe that Sam Altman is full of shit and the whole AI hype machine is a bubble (regardless of any real-world uses that do exist) built on lies about where this specific form of the technology can actually go, congratulations. You might enjoy listening to or reading the work of Ed Zitron. He has a podcast and a newsletter and he’s been pointing this out for over a year, among other topics.

  source
• NotASharkInAManSuit@lemmy.world ⁨2⁩ ⁨days⁩ ago

  That’s because they’re not trying to make AI, they are just programming LLMs to be bullshit confirmation bias machines. They don’t want to create intelligence, they want to create unregulated revenue streams.

  source
• jj4211@lemmy.world ⁨19⁩ ⁨hours⁩ ago

  I saw one article actually going all in on how incredible GPT-5 was.

  oneusefulthing.org/…/gpt-5-it-just-does-stuff

  The thing is, the biggest piece that really made the author excited was the “startup idea” and it proceeded to generate a mountain of business-speak that says nothing. He proceeds to proclaim a whole team of MBAs would take hours to produce something so magnificent. This pretty much made him just lose it, and I guess that is exactly the sort of content idiot executives slurp up.

  source
• Ghyste@sh.itjust.works ⁨2⁩ ⁨days⁩ ago

  Always has been.

  source
• ExLisper@lemmy.curiana.net ⁨1⁩ ⁨day⁩ ago

  One thing I didn’t expect in AI evolution was all the “safety” features. Basically since people are to stupid to use LLMs and not fall in love or poison themselves all models have more and more guardrails making it way less useful than normal search. I think it was fairly clear from the beginning that LLMs will always be bullshit machines but I didn’t think they will be less and less useful bullshit machines.

  source
• brsrklf@jlai.lu ⁨2⁩ ⁨days⁩ ago

  Somehow the chatGPT US map generated a clean, correctly spelled French word for “Mondays” instead of Illinois.

  Sorry, Illinois, Garfield hates your guts.

  source
• miridius@lemmy.world ⁨1⁩ ⁨day⁩ ago

  Nothing to see here, just another “token based LLMs can’t count letters in words” post

  source

  • shane@feddit.nl ⁨1⁩ ⁨day⁩ ago

    That’s what I thought but there’s slightly more than that.

    The writer tried to trick ChatGPT 5, saying Vermont has no R in it. ChatGPT did say “wait, it does”. But then when pushed it said, “oh right there is no R in Vermont”.

    I mean… the inability to know what it knows or not is a real problem for most use cases…

    source

    • jj4211@lemmy.world ⁨1⁩ ⁨day⁩ ago

      Yeah, the fact you can “gaslight” a chat is just as much of a symptom of a difficulty as the usual mistakes. It shows that it doesn’t deal with facts, but structurally sound content, which is correlated with facts, especially when the prompt has context/rag stuffing the prompt using more traditional approaches that actually will tend to get more factual stuff crammed in.

      To all the people white knighting for the LLM, for the thousandth time, we know that it is useful, but it’s usefulness is only tenuously connected to the marketing reality. Making the mistake in counting letters is less important than the fact that it “acts” like it can when it can’t.

      source
• misterdoctor@lemmy.world ⁨2⁩ ⁨days⁩ ago

  As a friend and AI defender recently put it

  This feels like an oxymoron

  source
• paraphrand@lemmy.world ⁨2⁩ ⁨days⁩ ago

  So is SamA.

  source
• DeathToUS@lemmy.world ⁨2⁩ ⁨days⁩ ago

  Just use DeepAI never bothered with ChatGPT because its so primitive same goes for Gemini.

  source
• Mereo@lemmy.ca ⁨2⁩ ⁨days⁩ ago

  I ran the tests with the thinking model. It got them right. For these kind of tasks, choosing the thinking model is key,

  source

  • very_well_lost@lemmy.world ⁨2⁩ ⁨days⁩ ago

    the thinking model

    Ugh… can we all just stop for a moment to acknowledge how obnoxious this branding is? They’ve already corrupted the term “AI” to the point of being completely meaningless, are they going to remove all meaning from the word “thinking” now too?

    source

    • Lemminary@lemmy.world ⁨2⁩ ⁨days⁩ ago

      They’ve already corrupted the term “AI” to the point of being completely meaningless

      Did they? Afaik, LLMs are an application of AI that falls under natural language processing. It’s like calling a rhombus a geometric shape because that’s what it is. And this usage goes back decades to, for example, A* pathfinding algorithms and hard-coded decision trees for NPCs.

      source

      • -> View More Comments