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

591–600 of 1001 posts

Re: ChatGPT Plugins

#591

Post by KyeRussell »

drexlspivey wrote: post #551
chatmasta wrote: post #353

Earlier quoted context omitted.

Pshhh... I think it's awesome. The faster we build the future, the better. What annoys me is this is just further evidence that their "AI Safety" is nothing but lip-service, when they're clearly moving fast and breaking things. Just the other day they had a bug where you could see the chat history of other users! (Which, btw, they're now claiming in a modal on login was due to a "bug in an open source library" - anyo…

> To be fair, this is basically what they're doing if you hit their APIs, since it's up to you whether or not to use their moderation endpoint. The model is neutered whether you hit the moderation endpoint or not. I made a text adventure game and it wouldn't let you attack enemies or steal, instead it was giving you a lecture on why you shouldn't do that.

It sounds like your prompt needs work then. Not in a “jailbreak” way, just in a prompt engineering way. The APIs definitely let you do much worse than attacking or stealing hypothetical enemies in a video game.

Re: ChatGPT Plugins

#592

Post by joe_the_user »

AOsborn wrote: post #501
joe_the_user wrote: post #263

Earlier quoted context omitted.

"Impressive and disturbing", So, ChatGPT is controlled by prompt engineering, plugins will work by prompt engineering. Both often work remarkably well. But none is really guaranteed to work as intended, indeed since it's all natural language, what's intended itself will remain a bit fuzzy to the humans as well. I remember the observation that deep learning is technical debt on steriods but I'm sure what this is. I su…

> But none is really guaranteed to work as intended, indeed since it's all natural language, what's intended itself will remain a bit fuzzy to the humans as well. Yeah, you're completely correct. But this is exactly the same as having a very knowledgeable but inexperienced person on your team. Humans get things wrong too. All this data is best if you have the experience or context to verify and confirm it. I heard a…

It seems like you're talking about using ChatGPT for research or code creation and that's reasonable advice for that.

But as far as I can tell, the link is to plugins, Expedia is listed as an example. So it seems they're talking about making ChatGPT itself (using extra prompts) be a company's chatbot that directly does things like make reservations from users instructions. That's what I was commenting on and that, I'd guess could a new and more dangerous kind of problem.

Re: ChatGPT Plugins

#593

Post by cawest11 »

qup wrote: post #332
chrispogeek wrote: post #297

Earlier quoted context omitted.

Owning up to the "wrong" is good in my book

That's just some weird moral compass. It's almost totally irrelevant if people own up to bring wrong, particularly about predictions. I can't think of a benefit, really. You can learn from mistakes without owning up to them, and I think that's the best use of mistakes.

No, it’s not. Being willing to admit you were wrong is foundational if you ever plan on building on ideas. This was a galaxy brained take if I’ve ever seen one.

Re: ChatGPT Plugins

#594

Post by fryry »

dragonwriter wrote: post #341
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…

> And OpenAI talks on and on about 'Safety' but all that 'Safety' means is "well, we didn't let anyone allow it to make jokes about fat or disabled people so we're good, right?!" No, OpenAI “safety” means “don’t let people compete with us”. Mitigating offensive content is just a way to sell that. As are stoking... exactly the fears you cite here, but about AI that isn’t centrally controlled by OpenAI.

It's a weird focus comparing it with how the internet developed in a very wild west way. Imagine if internet tech got delayed until they could figure out how to not have it used for porn.

Saftey from what exactly? The AI being mean to you? Just close the tab. Saftey to build a business on top? It's a self described research preview, perhaps too early to be thinking about that. Yet new releases are delayed for months for 'saftey'

Re: ChatGPT Plugins

#595

Post by jweir »

chatmasta wrote: post #418
jehb wrote: post #370

Earlier quoted context omitted.

> The faster we build the future, the better. Why? Getting to "the future" isn't a goal in and of itself. It's just a different state with a different set of problems, some of which we've proven that we're not prepared to anticipate or respond to before they cause serious harm.

When in human history have we ever intentionally not furthered technological progress? It's simply an unrealistic proposition, especially when the costs of doing it are so low that anyone with sufficient GPU power and knowledge of the latest research can get pretty close to the cutting edge. So the best we can hope for is that someone ethical is the first to advance that technological progress. I hope you wouldn't ad…

I look around me and see a wealthy society that has said no to a lot of technological progress - but not all. These are people that work together to build as a community to build and develop their society. They look at technology and ask if will be beneficial to the community and help preserve it - not fragment it.

I am currently on the outskirts of Amish country.

BTW when they come together to raise a barn it is called a frolic. I think we can learn a thing or two from them. And they certainly illustrate that alternatives are possible.

Re: ChatGPT Plugins

#596

Post by KyeRussell »

chatmasta wrote: post #353
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…

Pshhh... I think it's awesome. The faster we build the future, the better. What annoys me is this is just further evidence that their "AI Safety" is nothing but lip-service, when they're clearly moving fast and breaking things. Just the other day they had a bug where you could see the chat history of other users! (Which, btw, they're now claiming in a modal on login was due to a "bug in an open source library" - anyo…

Shhh! Don’t tell anyone! Getting access to the unmoderated model via the API / Playground is a surprisingly well-kept “secret” seeing as there are entire communities of people hell bent on pouring so much effort into getting ChatGPT to do things that the API will very willingly do. The longer it takes for people to cotton on, the better. I fully expect that OpenAI is using this as a honeypot to fine-tune their hard-stop moderation, but for now, the API is where it’s at.

Re: ChatGPT Plugins

#597

Post by LelouBil »

The browser example seems so much better than Bing Chat !

When I tried bing, it made at most 2 searches right after my question but the second one didn't seem to be based on the first one's content.

This can do multiple queries based on website content and follow links !

Re: ChatGPT Plugins

#598

Post by phatfish »

93po wrote: post #467
willmeyers wrote: post #392

Earlier quoted context omitted.

It's exciting and cool, but don't quit your job based on an emotional decision I'm just skeptical on how OpenAI fixes the blog spam issue you mentioned. Im sure someone has already started doing the math on how to game these systems and ensure that when you ask ChatGPT for recipe recs, it's going to spout the same spam (maybe worded a bit differently) and we'll soon all get tired of it again. Everything's changing, b…

Definitely not an emotional decision. I strongly believe we're going to see a massive shift for rational reasons :) OpenAI fixes this issue by not giving you two pages of the history of this recipe and the grandmother that originated it and what the author's thoughts are about the weather. It's just the recipe. No ads. No referral links. No slideshows. You don't have to click through three useless websites to find on…

> No Ads

At the moment. Although, this does seem like a chance to reset the economics of the "web". I can see enough people be willing to pay a monthly fee for an AI personal assistant that is genuinely helpful and saves time (so not the current Alexa/smart speaker nonsense), that advertising won't be the main monetization path anymore.

But, once all the eyeballs are on a chatbot rather than Google.com what for-profit company won't start selling advertising against that?

There is also the question what happens to the original content these LLMs need to actually make their statistical guess at the next word. If no one looks at the source anymore and its all filtered through an LLM is there any reason to publish to the web? Even hobbyists with no interest in making any money might balk knowing that they are just feeding an AI text.

Re: ChatGPT Plugins

#599

Post by seydor »

s1mon wrote: post #234

I know a large commercial entity will never do this, but I'd love to see a Sci-Hub plugin connected with the Wolfram plugin and whatever other plugins help to understand various realms of study. Imagine being able to ask ChatGPT to dig through research and answer questions based on those papers and theses.

Google scholar already has access to everything published. I hope their chatbot version does that

Re: ChatGPT Plugins

#600

Post by Ozzie_osman »

doctoboggan wrote: post #83
celestialcheese wrote: post #39

This is a big deal for openai. Been working with homegrown toolkits and langchain, the open source version of this, for a number of months and the ability to call out to vectorstores, serpapis, etc, and chaining together generations and data-retrieval really unlocks the power of the LLMs. That being said, I'd never build anything dependent on these plugins. OpenAI and their models rule the day today, but who knows wh…

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…

> 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.

I love langchain, but this argument overlooks the fact that closed, proprietary platforms have won over open ones all the time, for reasons like having distribution, being more polished, etc (ie windows over *nix, ios, etc).

Post reply on HN