I still can’t decide if these people are delusional or I am.
Every single time I use an LLM it fucking “lies” to me or otherwise completely fails at the task. The people talking like this seem to me like they’ve never actually used it, or haven’t actually vetted the accuracy (like most AI users).
Maybe I’m just not using the “good stuff”. Or I’m not imaginative enough to foresee a near future where these problems are actually corrected and it becomes trustworthy.
I’ve never been so torn by a technological prediction.
I’m curious what you are using. The free versions of chatgpt have been like that for me, but even Gemini flash with extended thinking, also free for a while longer, is giving me pretty reliable results as long as there training data out there to derive an answer from. The higher (paid) Claude models will one shot most coding tasks.
Yeah a lot of things in the old homelab had gotten pretty out of hand, homeassistant was 3 years behind in updates. I’ve done 2 years of updates in a month. And written some custom stock charting software which saves me hundreds a month in subscription fees.
I’ve not yet fucked with Claude. I don’t want to pay for it, and I really don’t like the surveillance aspect of these centralized systems. Mostly I’m using Gemini, whatever DDG had in their search results, and local models I’ve been fiddling with (like Qwen3.8 right now).
All more or less garbage once I get into the details of anything on the edge of my expertise.
Are you using Gemini in flash extended thinking? (Not flash light) . I haven’t had many hallucinations other than cases where the training data it needs just doesn’t exist (cases where I can’t find the answers by googling either)
Yes, LLMs make mistakes, but even small, self-hosted ones are pretty efficient today if you prompt them well. They’re not mind reading software so you need to be able to describe the task and HOW you want it done, not just barf in some basic instructions like “write me a copy of Facebook but better”.
It sounds like you’re saying people still need to be smart enough to use them properly… Which will be a problem as people rely on them more and more, and in turn become more stupid.
Yes it does. Just need to go beyond prompt. Add reinforcement loops, make it test the solution in a separate environ it can’t screw up in, and have it not just INVENT things (“give me X”), but research the topic and base its solution on the rules created by the research.
This is what basically the Claude harness (not the local but the remote harness you can’t see) adds to the LLM what makes it so powerful and useful. Replicate those processes and even a small 4B mode will be incredibly capable.
I’m in college and for one of my classes we actually have a prompt we feed to ChatGPT so that ChatGPT creates an excel spreadsheet for us as a step in an assignment process. The whole spreadsheet.
The class is for healthcare and I won’t get more specific, but yes, you can use AI today to make whole ass Excel spreadsheets.
(One of the steps in that particular assignment involves fact-checking the spreadsheet, btw, but about 95% of the time all the answers are word-for-word in the book, 4% they’re taken from the web and have more up-to-date info than the book has, and 1% is blatant lies.)
Tbh I’m old. The first computer I ever used didn’t even have a GUI. That a machine can take my specs and spit out a spreadsheet is fucking unbelievable to me, and I refuse to become so jaded that I can’t be impressed with the leaps forward that stuff makes.
This isn’t me being jaded. This is me saying “whole ass Excel spreadsheets” is an extremely low bar. Especially when almost two trillion dollars was pissed away getting it here. Imagine if someone had pumped that money into literally anything else.
Yeah, so far when someone shows me a concrete example of this amazingly complicated thing that GenAI helped then realize, I think “really… that’s it?”
It’s a decent reminder that a lot of people have more modest needs and a lot of the enthusiasm can come from that, and maybe that’s more understandable.
Why do you think “making” a “whole spreadsheet” is even impressive?
People fearmonger about those of us who are unimpressed with AI will be “left behind”, but its the pro AI prople who seem unable to comprehend how to do the most basic tasks.
Ya’ll the ones letting yourselves fall behind by not bothering to learn how to do the even the basics.
I’m 40. I can waste 40 minutes making this spreadsheet myself, or have an AI do it in like, 2 minutes. It’s not about not knowing how, it’s about not having to do the thing I know how to do anymore.
I still can’t decide if these people are delusional or I am.
Every single time I use an LLM it fucking “lies” to me or otherwise completely fails at the task. The people talking like this seem to me like they’ve never actually used it, or haven’t actually vetted the accuracy (like most AI users).
Maybe I’m just not using the “good stuff”. Or I’m not imaginative enough to foresee a near future where these problems are actually corrected and it becomes trustworthy.
I’ve never been so torn by a technological prediction.
I’m curious what you are using. The free versions of chatgpt have been like that for me, but even Gemini flash with extended thinking, also free for a while longer, is giving me pretty reliable results as long as there training data out there to derive an answer from. The higher (paid) Claude models will one shot most coding tasks.
Use Claude and then get back to me
I’ve been using it daily.
It’s been so useful to me. It’s crazy.
Yeah a lot of things in the old homelab had gotten pretty out of hand, homeassistant was 3 years behind in updates. I’ve done 2 years of updates in a month. And written some custom stock charting software which saves me hundreds a month in subscription fees.
I’ve not yet fucked with Claude. I don’t want to pay for it, and I really don’t like the surveillance aspect of these centralized systems. Mostly I’m using Gemini, whatever DDG had in their search results, and local models I’ve been fiddling with (like Qwen3.8 right now).
All more or less garbage once I get into the details of anything on the edge of my expertise.
Are you using Gemini in flash extended thinking? (Not flash light) . I haven’t had many hallucinations other than cases where the training data it needs just doesn’t exist (cases where I can’t find the answers by googling either)
Your experience is pretty unique then.
Yes, LLMs make mistakes, but even small, self-hosted ones are pretty efficient today if you prompt them well. They’re not mind reading software so you need to be able to describe the task and HOW you want it done, not just barf in some basic instructions like “write me a copy of Facebook but better”.
It sounds like you’re saying people still need to be smart enough to use them properly… Which will be a problem as people rely on them more and more, and in turn become more stupid.
No amount of prompt “engineering” will help when they outright make shit up.
Yes it does. Just need to go beyond prompt. Add reinforcement loops, make it test the solution in a separate environ it can’t screw up in, and have it not just INVENT things (“give me X”), but research the topic and base its solution on the rules created by the research.
This is what basically the Claude harness (not the local but the remote harness you can’t see) adds to the LLM what makes it so powerful and useful. Replicate those processes and even a small 4B mode will be incredibly capable.
I’m in college and for one of my classes we actually have a prompt we feed to ChatGPT so that ChatGPT creates an excel spreadsheet for us as a step in an assignment process. The whole spreadsheet.
The class is for healthcare and I won’t get more specific, but yes, you can use AI today to make whole ass Excel spreadsheets.
(One of the steps in that particular assignment involves fact-checking the spreadsheet, btw, but about 95% of the time all the answers are word-for-word in the book, 4% they’re taken from the web and have more up-to-date info than the book has, and 1% is blatant lies.)
lol, it amazes me what some people are impressed by
Tbh I’m old. The first computer I ever used didn’t even have a GUI. That a machine can take my specs and spit out a spreadsheet is fucking unbelievable to me, and I refuse to become so jaded that I can’t be impressed with the leaps forward that stuff makes.
This isn’t me being jaded. This is me saying “whole ass Excel spreadsheets” is an extremely low bar. Especially when almost two trillion dollars was pissed away getting it here. Imagine if someone had pumped that money into literally anything else.
Yeah, so far when someone shows me a concrete example of this amazingly complicated thing that GenAI helped then realize, I think “really… that’s it?”
It’s a decent reminder that a lot of people have more modest needs and a lot of the enthusiasm can come from that, and maybe that’s more understandable.
It’s a decent reminder that the kids are not alright.
Why do you think “making” a “whole spreadsheet” is even impressive?
People fearmonger about those of us who are unimpressed with AI will be “left behind”, but its the pro AI prople who seem unable to comprehend how to do the most basic tasks.
Ya’ll the ones letting yourselves fall behind by not bothering to learn how to do the even the basics.
I’m 40. I can waste 40 minutes making this spreadsheet myself, or have an AI do it in like, 2 minutes. It’s not about not knowing how, it’s about not having to do the thing I know how to do anymore.