I suppose the issue here is more semantics than anything, yeah. I think better discussion would be had if the topic was “how can we help LLMs better understand and present information,” as opposed to a more sensational “GPT will cheat and lie”
I think the reason I’m not comfortable with using the term “lying” is because it implies some sort of negative connotation. When you say that someone lies, it comes with an understanding that they made a choice to lie, usually with ill intent. I agree, we don’t need to get into a philosophical discussion on choice and free will. But I think saying something like “GPT lies” is a bit irresponsible for the purposes of a discussion
They said “it just repeats words that simulate human responses,” and I’d say that concisely answers your question.
Antropomorphizing inanimate objects and machines is fine for offering a rough explanation of what is happening, but when you’re trying to critically evaluate something, you probably want to offer a more rigid understanding.
In this case, it might be fair to tell a child that the AI is lying to us, and that it’s wrong. But if you want a more serious discussion on what GPT is doing, you’re going to have to drop the simple explanation. You can’t ascribe ethics to what GPT is doing here. Lying is an ethical decision, one that GPT doesn’t make.
Would love to deploy this, but unfortunately I’m running server equipment that apparently doesn’t support MongoDB 5 (Error message MongoDB 5.0+ requires a CPU with AVX support, and your current system does not appear to have that!). Tried deploying with both 4.4.18 and 4.4.6 and can’t get it to work. If anybody has some recommendations, I’d appreciate hearing them!
Edit: Changed my proxmox environment processor to host, fixed my issue.
Hmm, I’ve never looked into qemu. Do you use a GPU in your environment? It passes through to your Windows VM fine?
On my host PC (Windows Server), I’m already running a VM in Hyper-V that operates behind a VPN for my *arr environment. I’m worried about resources and resource allocation if I add another VM just for docker. Basically I’m looking at 3 environments - Windows Server for my windows stuff, Debian server for my *arr stuff (this all has to be behind a VPN), and a Linux docker environment. It makes sense to me to go the Proxmox route now that I’ve considered it, don’t you think? Not asking because I’m trying to convince you, just interested in others perspectives.
That’s what I’ve been seeing, but I run enough stuff on Windows that has poor support for Linux that makes it a toss-up. Do you think it’s feasible to run Docker on Linux in a Hyper-V container on Windows? I’m really trying to evaluate my options, I’ve considered Proxmox to separate my Windows and Linux stuff; currently I am running an instance of Ubuntu in Hyper-V for my Linux stuff. Do you think Proxmox is more viable?
I used to have this issue more often as well. I’ve had good results recently by **not ** pointing out mistakes in replies, but by going back to the message before GPT’s response and saying “do not include y.”