give an example please, because i don’t see how in normal use the weighting would matter at a significant scale based on the massive volume of training data
any interact the chatbot has with one person is dwarfed by the amount of total text data the AI has consumed through training. it’s like saying saggitarius a gets changed over time by adding in a few planets. while definitely true it’s going to be a very small effect
The reason is that the web browser chatgpt has a maximum amount of data per request. This is so they can minimize cost at scale. So for example you ask a question and tell it not to include a word. What will happen is your questions gets sent like this
{‘context’: ‘user asking question’, ‘message’: {user question here} }
then it gives you a response and you ask it another question. typically if it’s a small question the context is saved from one message to another.
{‘context’: ‘user asking question - {previous message}’, ‘message’: {new message here} }
so it literally just copies the previous message until it reaches the maximum token length
however there’s a maximum # of words that can be in the context + message combined. therefore the context is limited. after a certain amount of words input into chatgpt, it will start dropping things. it does this with a method to try and find out what is the “most important words” but this is inherently lossy. it’s like a jpeg- it gets blurry in order to save data.
so for example if you asked “please name the best fruit to eat, not including apple” and then maybe on the third or fourth question the “context” in the request becomes
‘context’: ‘user asking question - user wanted to know best fruit’
it would cut off the “not including apple bit” in order to save space
but here’s the thing - that exists in order to save space and processing power. it’s necessary at a large scale because millions of people could be talking to chatgpt and it couldn’t handle all that.
BUT if chatgpt wanted some sort of internal request that had no token limit, then everything would be saved. it would turn from a lossy jpeg into a png file. chatgpt would have infinite context.
this is why i think for someone who wants to keep context (ive been trying to develop specific applications which context is necessary) then chatgpt api just isn’t worth it.
very short term memory span so have longer conversations as in more messages
Really, this is a function of practicality and not really one of capability. If someone were to give an LLM more context it would be able to hold very long conversations. It’s just that it’s very expensive to do so on any large scale - so for example OpenAI’s API gives a maximum token length to requests.
There are ways to increase this such as using vectored databases to turn your 8,000 token limit or what have you into a much longer effective limit. And this is how you preserve context.
When you talk to ChatGPT in the web browser, it’s basically sending a call to its own API and re-sending the last few messages (or what it thinks is most important in the last few messages) but that’s inherently lossy. After enough messages, context gets lost.
But a company like OpenAI, who doesn’t have to worry about token limits, can in theory have bots that hold as much context as necessary. So while your advice is good in a practical sense - most chatbots you run into will likely have those limits because of financial reasons… it is in theory possible to have a chatbot that doesn’t have these limits and therefore this strategy would not work.
Fedora. I’d avoid Ubuntu and its derivatives like Pop! or Arch derivatives. I think Arch is fine, especially if you know what you’re doing, but Arch derivatives in my experience are much less stable than for example Ubuntu or Fedora.
But seriously. Fedora. It’s the best. Ubuntu is actually fine too but Blue > Orange
Chega de frescura e come o ovo de uma vez
I’ve been using the same distro for at least 4 years now and I haven’t ever had any issues. Fedora on a desktop at home. It’s very stable. You don’t even need to know too much… although obviously knowing your way around the terminal and knowing some basic things about Linux helps
applications are installed with flatpak - basically little containers that contain everything a program needs. sort of like docker
so normally if you wanna install something - let’s say minecraft. you would also need to install java. the flatpak for minecraft would have java inside of it so it can be run in its own little container and you don’t need to install either
I’ve been driving for about a decade and a half now, including a few years here and there working jobs with a lot of wheel time. Either pizza delivery or cable technician or driving around a box truck.
I have never gotten as much as a speeding ticket. I typically don’t speed more than 5~10 mph over the limit. If it’s a 35 or 40 in a city area though I will typically stay the speed limit. Sometimes I go a little ham on country roads in the middle of nowhere. I drove through central Florida once at like 4am and I peaked at like 120mph because I hadn’t seen another car for at least an hour.
I think it probably depends on your jurisdiction, but nobody really respects the laws. On the interstate near my house, the speed limit is 65 but it might as well be 80. Cops will pass you and people will pass the cops and nobody cares.
I think the speeding laws are just to give the cops a reason to pull you over if they want you - OR a way to get people that are really being crazy. For example if you’re going 110 in a 65 you deserve to get pulled over and given a ticket or worse, depending on context.