LLM advocates still don’t seem to be able to comprehend that ordering the machine not to ‘make stuff up’ doesn’t help.
-
LLM advocates still don’t seem to be able to comprehend that ordering the machine not to ‘make stuff up’ doesn’t help. It doesn’t know when it’s making stuff up, and it couldn’t change that even if you told it to. (In fact it’s always just making stuff up, and is only ever true by chance.)
Part of why I’m so negative about them is that their advocates simply do not understand how they work and do not seem to want to.
Dare Obasanjo (@carnage4life@mas.to)
Attached: 1 image Hallucinations are the bane of my existence when using Claude Code and that has significantly improved after adding the following instructions to my Claude .MD file. Sharing for anyone else who uses Claude as a daily driver for analysis and writing but has gotten frustrated by it making things up.
mas.to (mas.to)
-
LLM advocates still don’t seem to be able to comprehend that ordering the machine not to ‘make stuff up’ doesn’t help. It doesn’t know when it’s making stuff up, and it couldn’t change that even if you told it to. (In fact it’s always just making stuff up, and is only ever true by chance.)
Part of why I’m so negative about them is that their advocates simply do not understand how they work and do not seem to want to.
Dare Obasanjo (@carnage4life@mas.to)
Attached: 1 image Hallucinations are the bane of my existence when using Claude Code and that has significantly improved after adding the following instructions to my Claude .MD file. Sharing for anyone else who uses Claude as a daily driver for analysis and writing but has gotten frustrated by it making things up.
mas.to (mas.to)
its because the majority of LLM advocates were poor programmers in the first place
-
its because the majority of LLM advocates were poor programmers in the first place
it also explains why companies are so gung ho about LLMs - it covers up their selection & training of programmers
-
LLM advocates still don’t seem to be able to comprehend that ordering the machine not to ‘make stuff up’ doesn’t help. It doesn’t know when it’s making stuff up, and it couldn’t change that even if you told it to. (In fact it’s always just making stuff up, and is only ever true by chance.)
Part of why I’m so negative about them is that their advocates simply do not understand how they work and do not seem to want to.
Dare Obasanjo (@carnage4life@mas.to)
Attached: 1 image Hallucinations are the bane of my existence when using Claude Code and that has significantly improved after adding the following instructions to my Claude .MD file. Sharing for anyone else who uses Claude as a daily driver for analysis and writing but has gotten frustrated by it making things up.
mas.to (mas.to)
@benjamineskola Obasanjo is such a (1) moron, and (2) over-exposed piece of shit.
-
@benjamineskola Obasanjo is such a (1) moron, and (2) over-exposed piece of shit.
@prietschka I do recall that a few weeks back he was complaining that LLM advocates get made to feel unwelcome on the fediverse. (OK? I don’t care. It’s nobody’s job to make people feel good about their bad opinions.)
And then just a couple of days ago he was posting something critical, and like … yes this is what we’ve been saying all along.
-
LLM advocates still don’t seem to be able to comprehend that ordering the machine not to ‘make stuff up’ doesn’t help. It doesn’t know when it’s making stuff up, and it couldn’t change that even if you told it to. (In fact it’s always just making stuff up, and is only ever true by chance.)
Part of why I’m so negative about them is that their advocates simply do not understand how they work and do not seem to want to.
Dare Obasanjo (@carnage4life@mas.to)
Attached: 1 image Hallucinations are the bane of my existence when using Claude Code and that has significantly improved after adding the following instructions to my Claude .MD file. Sharing for anyone else who uses Claude as a daily driver for analysis and writing but has gotten frustrated by it making things up.
mas.to (mas.to)
@benjamineskola Just bonkers stuff coming from someone who should probably know better. Dare remains on my block list, just not worth listening to anything he says.
-
R relay@relay.an.exchange shared this topic
-
LLM advocates still don’t seem to be able to comprehend that ordering the machine not to ‘make stuff up’ doesn’t help. It doesn’t know when it’s making stuff up, and it couldn’t change that even if you told it to. (In fact it’s always just making stuff up, and is only ever true by chance.)
Part of why I’m so negative about them is that their advocates simply do not understand how they work and do not seem to want to.
Dare Obasanjo (@carnage4life@mas.to)
Attached: 1 image Hallucinations are the bane of my existence when using Claude Code and that has significantly improved after adding the following instructions to my Claude .MD file. Sharing for anyone else who uses Claude as a daily driver for analysis and writing but has gotten frustrated by it making things up.
mas.to (mas.to)
@benjamineskola reminds me of meeting with the business side of my job and the marketing people keep thinking if they word the requirements juuuuust right suddenly I'll be able to do the impossible.
-
LLM advocates still don’t seem to be able to comprehend that ordering the machine not to ‘make stuff up’ doesn’t help. It doesn’t know when it’s making stuff up, and it couldn’t change that even if you told it to. (In fact it’s always just making stuff up, and is only ever true by chance.)
Part of why I’m so negative about them is that their advocates simply do not understand how they work and do not seem to want to.
Dare Obasanjo (@carnage4life@mas.to)
Attached: 1 image Hallucinations are the bane of my existence when using Claude Code and that has significantly improved after adding the following instructions to my Claude .MD file. Sharing for anyone else who uses Claude as a daily driver for analysis and writing but has gotten frustrated by it making things up.
mas.to (mas.to)
@benjamineskola like, fundamentally it has no concept of truth so it cannot evaluate the truthiness of any statement
-
@benjamineskola like, fundamentally it has no concept of truth so it cannot evaluate the truthiness of any statement
@solonovamax yes, that is my point
-
LLM advocates still don’t seem to be able to comprehend that ordering the machine not to ‘make stuff up’ doesn’t help. It doesn’t know when it’s making stuff up, and it couldn’t change that even if you told it to. (In fact it’s always just making stuff up, and is only ever true by chance.)
Part of why I’m so negative about them is that their advocates simply do not understand how they work and do not seem to want to.
Dare Obasanjo (@carnage4life@mas.to)
Attached: 1 image Hallucinations are the bane of my existence when using Claude Code and that has significantly improved after adding the following instructions to my Claude .MD file. Sharing for anyone else who uses Claude as a daily driver for analysis and writing but has gotten frustrated by it making things up.
mas.to (mas.to)
@benjamineskola I don't partake on the LLM stuff but they've already proved some degree of usefulness.
I don't think people in general would trust them with sensitive (health, well being) stuff but from what I hear, some people are very good at wielding it as a tool.
I don't know how my car works, I'd be a terrible mechanic and racer. Still, it's very handy tool for me to move around.
-
LLM advocates still don’t seem to be able to comprehend that ordering the machine not to ‘make stuff up’ doesn’t help. It doesn’t know when it’s making stuff up, and it couldn’t change that even if you told it to. (In fact it’s always just making stuff up, and is only ever true by chance.)
Part of why I’m so negative about them is that their advocates simply do not understand how they work and do not seem to want to.
Dare Obasanjo (@carnage4life@mas.to)
Attached: 1 image Hallucinations are the bane of my existence when using Claude Code and that has significantly improved after adding the following instructions to my Claude .MD file. Sharing for anyone else who uses Claude as a daily driver for analysis and writing but has gotten frustrated by it making things up.
mas.to (mas.to)
That's funny when you explain to people how it really works, if they are not LLM advocates, they see exactly why it can't work.
It's literally created with to make stuff up.
-
@benjamineskola I don't partake on the LLM stuff but they've already proved some degree of usefulness.
I don't think people in general would trust them with sensitive (health, well being) stuff but from what I hear, some people are very good at wielding it as a tool.
I don't know how my car works, I'd be a terrible mechanic and racer. Still, it's very handy tool for me to move around.
@junkman sorry, did I seem like I was interested in yet another defence of LLMs?
-
LLM advocates still don’t seem to be able to comprehend that ordering the machine not to ‘make stuff up’ doesn’t help. It doesn’t know when it’s making stuff up, and it couldn’t change that even if you told it to. (In fact it’s always just making stuff up, and is only ever true by chance.)
Part of why I’m so negative about them is that their advocates simply do not understand how they work and do not seem to want to.
Dare Obasanjo (@carnage4life@mas.to)
Attached: 1 image Hallucinations are the bane of my existence when using Claude Code and that has significantly improved after adding the following instructions to my Claude .MD file. Sharing for anyone else who uses Claude as a daily driver for analysis and writing but has gotten frustrated by it making things up.
mas.to (mas.to)
@benjamineskola "hey convincing-bullshit-a-tron2000, i want you to stop making up bullshit when you answer to me"
"ok" -
@junkman sorry, did I seem like I was interested in yet another defence of LLMs?
@benjamineskola nah, man. You do you, proceed with the dunking.
-
@benjamineskola like, fundamentally it has no concept of truth so it cannot evaluate the truthiness of any statement
@solonovamax @benjamineskola i feel like it's more that it just wasn't built to give out answers, it was trained not to answer truthfully and "understand" but to just come up with something that sounds kind of convincing
-
@benjamineskola reminds me of meeting with the business side of my job and the marketing people keep thinking if they word the requirements juuuuust right suddenly I'll be able to do the impossible.
LLM are a Skinner Box.
-
That's funny when you explain to people how it really works, if they are not LLM advocates, they see exactly why it can't work.
It's literally created with to make stuff up.
@Aedius yes, like... if you accept that this is just how they work, you might be able to use them productively for the limited tasks they're capable of doing at. But refusing to understand the way they work and then yelling at them about it is just embarrassing.
-
@solonovamax @benjamineskola i feel like it's more that it just wasn't built to give out answers, it was trained not to answer truthfully and "understand" but to just come up with something that sounds kind of convincing
@nelson @solonovamax no, it's not capable of understanding. it's not a thing that this sort of technology could do.
-
@nelson @solonovamax no, it's not capable of understanding. it's not a thing that this sort of technology could do.
@benjamineskola @solonovamax yeah it's just good at knowing what the next word is, so it can string something mathematically coherent
kind of like how "ai art" tends to be extremely generic looking because it quite literally aims to pick the most average in its dataset for a specific prompt
-
@benjamineskola I don't partake on the LLM stuff but they've already proved some degree of usefulness.
I don't think people in general would trust them with sensitive (health, well being) stuff but from what I hear, some people are very good at wielding it as a tool.
I don't know how my car works, I'd be a terrible mechanic and racer. Still, it's very handy tool for me to move around.
@junkman like in all seriousness it's fine to have some degree of missing knowledge about how your car works, but if you believe that it's capable of avoiding collisions by itself and your method of reducing collisions is just to ask it to try harder, you'd be a danger to yourself and others.
I'm not asking people to have deep knowledge of the mathematics behind LLMs, but I do expect people who are actively advocating their adoption not to make up outright fantasies about how they work.
