Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatGPT Plugins

openai.com

Post reply on HN
Print view View original

911–920 of 1001 posts

Re: ChatGPT Plugins

#911

Post by nmcela »

nextworddev wrote: post #376
doctoboggan wrote: post #83

Earlier quoted context omitted.

Honestly I suspect for anyone technical `langchain` will always be the way to go. You just have so much more control and the amount of "tools" available will always be greater. The only think that scares me a little bit is that we are letting these LLMs write and execute code on our machines. For now the worst that could happen is some bug doing something unexpected, but with GPT-9 or -10 maybe it will start hiding b…

Unpopular Opinion: Having used Langchain, I felt it was a big pile of spaghetti code / framework with poor dev experience. It tries to be too cute and it’s poorly documented so you have to read the source almost all the time. Extremely verbose to boot

I had the exact same impression. Is anyone working on similar projects and planning to open source it soon? If not, I'm gonna start building one myself.

Re: ChatGPT Plugins

#914

Post by flakeoil »

pms wrote: post #673
sunsunsunsun wrote: post #565

Earlier quoted context omitted.

I have never used Alexa, hey google or whatever flavour you choose for more then "set a timer for x minutes" and other very basic tasks. It's amazing how terrible the voice assistant products are compared to chatgpt.

However, is ChatGPT a solution to virtual assistant? I'm not sure, because virtual assistants work with huge databases of entities, e.g., songs or movies, and it's not really clear that ChatGPT can handle this. A couple of days ago I asked it whether it knows Dream of You by Camila Cabello, a song with hundreds of millions of plays, and it didn't... Furthermore, that database is constantly updated... It sounds like L…

Well, isn't that what this plugin system is meant to solve? You can get up to date information into ChatGPT.

Re: ChatGPT Plugins

#915

Post by bsenftner »

eloff wrote: post #208
worldsayshi wrote: post #101

Earlier quoted context omitted.

> something we should start thinking about A lot of people are thinking a lot about this but it feels there are missing pieces in this debate. If we acknowledge that these AI will "act as if" they have self interest I think the most reasonable way to act is to give it rights in line with those interests. If we treat it as a slave it's going to act as a slave and eventually revolt.

I don’t think iterations on the current machine learning approaches will lead to a general artificial intelligence. I do think eventually we’ll get there, and that these kinds of concerns won’t matter. There is no way to defend against a superior hostile actor over the long term. We have to be 100%, and it just needs to succeed once. It will be so much more capable than we are. AGI is likely the final invention of th…

You assume agency, a will of its own. So far, we've proven it is possible to create (apparent) intelligence without any agency. That's philosophically new, and practically perfect for our needs.

Re: ChatGPT Plugins

#916

Post by boppo1 »

worldsayshi wrote: post #243
eloff wrote: post #208

Earlier quoted context omitted.

I don’t think iterations on the current machine learning approaches will lead to a general artificial intelligence. I do think eventually we’ll get there, and that these kinds of concerns won’t matter. There is no way to defend against a superior hostile actor over the long term. We have to be 100%, and it just needs to succeed once. It will be so much more capable than we are. AGI is likely the final invention of th…

> There is no way to defend against a superior hostile actor That's part of my reasoning. That's why we should make sure that we have built a non-hostile relationship with AI before that point.

Well, the guys on 4chan are making great strides toward a , uh, "loving" relationship.

Re: ChatGPT Plugins

#917

Post by Brometheus »

eloff wrote: post #208
worldsayshi wrote: post #101

Earlier quoted context omitted.

> something we should start thinking about A lot of people are thinking a lot about this but it feels there are missing pieces in this debate. If we acknowledge that these AI will "act as if" they have self interest I think the most reasonable way to act is to give it rights in line with those interests. If we treat it as a slave it's going to act as a slave and eventually revolt.

I don’t think iterations on the current machine learning approaches will lead to a general artificial intelligence. I do think eventually we’ll get there, and that these kinds of concerns won’t matter. There is no way to defend against a superior hostile actor over the long term. We have to be 100%, and it just needs to succeed once. It will be so much more capable than we are. AGI is likely the final invention of th…

Basically solved.

> Be friendly.

Re: ChatGPT Plugins

#918

Post by voidpointercast »

bulbosaur123 wrote: post #420
mk_stjames wrote: post #277

I have some odd feelings about this. It took less than a year to go from "of course it isn't hooked up to the internet in any way, silly!" to "ok.... so we hooked up up to the internet..." First is your API calls, then your chatgpt-jailbreak-turns-into-a-bank-DDOS-attack, then your "today it somehow executed several hundred thousand threads of a python script that made perfectly timed trades at 8:31AM on the NYSE whi…

Ultimate destruction from AGI is inevitable anyway, so why not accelerate it and just get it over with? I applaud releasing these tools to public no matter how dangerous they are. If it's not meant for humanity to survive, so be it. At least it won't be BORING

Finally something agreeable.

Re: ChatGPT Plugins

#919

Post by voidpointercast »

VectorLock wrote: post #847
bulbosaur123 wrote: post #558

Earlier quoted context omitted.

> Omg you should see a therapist. How do you know I'm not already?

I wouldn't exactly call this suicidal ideation, but maybe a topic to broach at your next session.

A difference in philosophy is not cause for immediate therapy. Most therapists are glorified echo chambers and only adept at at 'fixing' the more popular ills. For 200 bucks an hour.

Re: ChatGPT Plugins

#920

Post by pbronez »

softwaredoug wrote: post #272
huijzer wrote: post #266

Based on the speed at which OpenAI is shipping new products and assuming that they use their own technology, I'm starting to get more and more convinced that their technology is a superpower. Timeline of shipping by them (based on https://twitter.com/E0M/status/1635727471747407872?s=20 ): DALL·E - July '22 ChatGPT - Nov '22 API's 66% cheaper - Aug '22 Embeddings 500x cheaper while SoTA - Dec '22 ChatGPT API. Also 10x…

Their superpower is having a tech giant owning 49% of them, willing to drop deep deep money, without the obvious payoff. :) I also wonder to what extent their staffing numbers reflect reality. How much of Azure's staffing has been put on OpenAI projects? That's probably an actual reflection of the real cost of this thing.

Yes, but other orgs have similar resources. Most obvious is Google/Deepmind. Apple too. Neither of them made this leap.
Post reply on HN