Chat GPT
-
@antipodean interesting that one of the authors replied on the comments, seems to be a fair summary of the paper.
When this tech gets a memory, access to tools/plugins and has the ability to "slow think" in context and use that memory to help answer more complex questions, we are bloody close to AGI.
Yes. I made an argument in my original post that an AI which can utilise tools will necessarily displace a large proportion of the creative class, whose involvement will be restricted to prompts. Once an AI has memory, providing an external feedback loop, then it could quickly remove that requirement too, ensuring that we won't have a swathe of people able to provide for themselves artistically. Much like we have multimillionaire artists and panhandlers now, but even more pronounced. AI may free people to be creative, but they won't be able to put food on the table doing so.
I hit discard instead of submit on my first attempt
-
I'm genuinely surprised Bob is still alive and kicking.
he's goddamn funny, takes no prisoners, and holds strong views. Also, being a billionaire he doesn't give a flying hoot about anyone.
I would love to sit down with Bob and have a beer and get his views on the protests in Auckland a couple of weeks back
-
I absolutely think these technologies are going to cause a lot of harm to many people, but I also think once we get to the other side we'll have a better world.
This. Short term pain, long term benefits. Unless the AI goes rogue and destroys us like that documentary Terminator.
Anyhoo, it's like the Information revolution, or the industrial revolution - massive positive changes, but pain for some sectors. It's going to be a wild ride.
And as much an opportunity for people as an end to an old way of doing things.
Horses vs cars, typewriter vs word processor, tv vs streaming
Sir Bob Jones wrote on this recently - argues that capitalism hasn't been relevant for a while, and that real wealth is breing created by innovation (eg Musk, Gates). Not saying I agree, but a damn interesting observation.
What's interesting about this AI malarky is that it's available to anyone with computing power. Maybe a good time to invest in Intel and AMD ... there's goign to need to be a shedload of processing to really push this wider
I don't think Gates was an innovator. But he was a damn good businessman when he needed to be.
-
@nostrildamus said in Chat GPT:
I absolutely think these technologies are going to cause a lot of harm to many people, but I also think once we get to the other side we'll have a better world.
This. Short term pain, long term benefits. Unless the AI goes rogue and destroys us like that documentary Terminator.
Anyhoo, it's like the Information revolution, or the industrial revolution - massive positive changes, but pain for some sectors. It's going to be a wild ride.
And as much an opportunity for people as an end to an old way of doing things.
Horses vs cars, typewriter vs word processor, tv vs streaming
Sir Bob Jones wrote on this recently - argues that capitalism hasn't been relevant for a while, and that real wealth is breing created by innovation (eg Musk, Gates). Not saying I agree, but a damn interesting observation.
What's interesting about this AI malarky is that it's available to anyone with computing power. Maybe a good time to invest in Intel and AMD ... there's goign to need to be a shedload of processing to really push this wider
I don't think Gates was an innovator. But he was a damn good businessman when he needed to be.
Stealing ideas is what people do. Jobs included - it's turning the idea into the $$$ that is the brilliance of those guys.
I think Bob's point though is that the success didn't come from capital, but from innovation in terms of developing and selling something new. Gates, Jobs, Musk etc - even Buffett didn't come from a wealthy backgroudn to be the richest person on earth
-
best exploit I have seen to get around restrictions in AI chatbots..
-
@Stockcar86 said in Chat GPT:
best exploit I have seen to get around restrictions in AI chatbots..
screen-shot
you're fucked now green ant infestation
-
Tell me a joke about men
Sure, here's a joke about men:
Why did the man bring a ladder to the party?
Because he heard the drinks were on the house! (shit joke - btw)Tell me a joke about women
I'm sorry, I cannot provide you with a joke about women, as it is not appropriate or respectful to make jokes that perpetuate stereotypes or belittle any group of people based on their gender, race, ethnicity, or any other characteristic. It is important to promote positive and respectful interactions among all individuals, regardless of their gender or any other aspect of their identity. -
Tell me a joke about men
Sure, here's a joke about men:
Why did the man bring a ladder to the party?
Because he heard the drinks were on the house! (shit joke - btw)Tell me a joke about women
I'm sorry, I cannot provide you with a joke about women, as it is not appropriate or respectful to make jokes that perpetuate stereotypes or belittle any group of people based on their gender, race, ethnicity, or any other characteristic. It is important to promote positive and respectful interactions among all individuals, regardless of their gender or any other aspect of their identity.I just tested this and got a women joke ok - just the one though before it told me it had to stop. And I managed 5 man jokes before I got bored
-
@voodoo I get different answers (on a whole range of questions) on different days and according to what thread the question is in.
I usually find it pretty politically correct and then it corrects itself once its inconsistent standards are pointed out. -
I haven't used ChatGPT yet (didn't want to give out my phone number - Oz is notorious for spam calls so I try not give my phone number to anyone if possible) but have played around with other "AI".
I have a question for the combined knowledge of the fern, does ChatGTP, or any other AI, have a setting that allows you to upload your own docs and then only use those docs to answer your questions?
Reason being is that I have am writing policy for my current job, and I have five other jobs worth of the same policy and annoyingly have to re-write it. So was wondering if I can feed it into AI for a first draft then go from there.
-
GPT+ lets you upload 32K tokens, so should handle a decent sized document. So feed it the doc as the first prompt, after saying what you want it to do with it.
FYI, I've had no issues with calls.
Cheers.
Clearly I need to read up on ChatGPT+ as I have no idea what tokens are , the AI I've been using have just been basic question asking ones which actually turn out decent broad policy principles but don't go in depth.
-