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

841–850 of 1001 posts

Re: ChatGPT Plugins

#841

Post by sp332 »

unit_circle wrote: post #793
bsaul wrote: post #663

Earlier quoted context omitted.

In a way this is a bit less impressive than having chatgpt being able to generate those answers on its own only using learned information. This kinds of admits defeat regarding its ability to solve mathematical problems correctly or answer factual information.

But doesn't this seem like the correct approach long term? Basically shelling out to what essentially amounts to a fact table when it gets a factual question

Yes, there's no point spending all that time and compute training and inferring ways to do math problems when you could just use a calculator.

Re: ChatGPT Plugins

#842

Post by sp332 »

folli wrote: post #393
amrrs wrote: post #314

Here is ChatGPT's response of this HN thread tweeted by Greg - https://twitter.com/gdb/status/1638986918947082241 insane!

I'm still confused on the difference between ChatGPT and Bing Chat. When asking Bing Chat the exact same question, it won't be able to find this here HN thread and will reply about a 9to5google article about the topic. I thought Bing Chat uses GPT-4 as well?

Well, it does now.

There was a post on Hacker News about ChatGPT plugins by OpenAI 1. The post received 1333 points and 710 comments 1. One user commented that they were wrong about OpenAI missing out on generative AI art wave because they were focused on more high-impact products like ChatGPT, GPT4 and now plugins 1. Another user mentioned that it was clear from the start that OpenAI intended to monetize DALL-E but competitors were able to release viable alternatives before OpenAI could establish a monopoly 1.

Citation 1 links to this thread.

Re: ChatGPT Plugins

#843

Post by taco_philips »

judge2020 wrote: post #824
nwienert wrote: post #442

Earlier quoted context omitted.

We have a ton of protection laws around all sorts of dangerous technology, this is a super naive take. You can't buy tons of weapon technology, nuclear materials, aerosolized compounds, pesticides. These are all highly regulated and illegal pieces of technology for the better . In general the liberal position of progress = good is wrong in many cases, and I'll be thankful to see AI get neutered. If anything treat it…

> You can't buy tons of weapon technology, nuclear materials, aerosolized compounds, pesticides. These are all highly regulated and illegal pieces of technology for the better. Only because we know the risks and issues with them. OP is talking about furthering technology, which is quite literally "discovering new things"; regulations on furthering technology (outside of literal nuclear weapons) would have to be along…

[dead]

Re: ChatGPT Plugins

#844

Post by worldsayshi »

astrange wrote: post #807
TeMPOraL wrote: post #736

Earlier quoted context omitted.

Counterpoint: whatever you define as individual "AI person" entitled to some rights, that "species" will be able to reproduce orders of magnitude faster than us - literally at the speed of moving data through the Internet, perhaps capped by the rate at which factories can churn out more compute. So imagine you grant AI people rights to resources, or self-determination. Or literally anything that might conflict with o…

This kind of fantasy about AIs exponentially growing and multiplying seems to be based on pretending nobody's gonna have to pay the exponential power bills for them to do all this.

It's a good point but we don't really know how intelligence scales with energy consumption yet. A GPT-8 equivalent might run on a smartphone once it's optimized enough.

Re: ChatGPT Plugins

#845

Post by int_19h »

butterfly771 wrote: post #775
int_19h wrote: post #629

Earlier quoted context omitted.

Russia is already blocked from ChatGPT and Bing; I don't know about China. But it's all security theater. Plenty of people use it with VPNs, and I know several who found it useful / interesting enough to bother paying for it (which involves foreign credit cards etc so it's kind of a hassle). I'm sure so does the Russian govt. In any case, I don't see how you could realistically block any of that without effectively w…

I am from China, the Chinese government has banned access to chatgpt related products and Baidu has launched the 文心一言 which is basically gpt-3.

Wait, do you mean it's on par with GPT-3, or it's literally GPT-3? If the latter, how did they get the model?

Re: ChatGPT Plugins

#846

Post by taco_philips »

pmoriarty wrote: post #728
nwienert wrote: post #442

Earlier quoted context omitted.

We have a ton of protection laws around all sorts of dangerous technology, this is a super naive take. You can't buy tons of weapon technology, nuclear materials, aerosolized compounds, pesticides. These are all highly regulated and illegal pieces of technology for the better . In general the liberal position of progress = good is wrong in many cases, and I'll be thankful to see AI get neutered. If anything treat it…

"We have a ton of protection laws around all sorts of dangerous technology, this is a super naive take. You can't buy tons of weapon technology, nuclear materials, aerosolized compounds, pesticides. These are all highly regulated and illegal pieces of technology for the better." As technology advances, such prohibitions are going to become less and less effective. Tech is constantly getting smaller, cheaper and easie…

[dead]

Re: ChatGPT Plugins

#847

Post by VectorLock »

bulbosaur123 wrote: post #558
Mystery-Machine wrote: post #523

Earlier quoted context omitted.

Death is inevitable. Why not accelerate it? Omg you should see a therapist.

> 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.

Re: ChatGPT Plugins

#848

Post by VectorLock »

gtirloni wrote: post #400
alibarber wrote: post #390

Earlier quoted context omitted.

I'm also confused - maybe I'm missing something. Cannot I, or anyone else, already execute several hundred thousand 'threads' of python code, to do whatever, now - with a reasonably modest AWS/Azure/GCE account?

Yes. I think the point is that a properly constructed prompt will do that at some point, lowering the barrier of entry for such attacks.

Conceivably ChatGPT could help, with more suggestions for fuzzing that independently operating malicious actors may not have been able to synthesize.

Most of the really bad actors have skills approximately at or below those displayed by GPT-4.

Re: ChatGPT Plugins

#849

Post by chatmasta »

jacquesm wrote: post #816
chatmasta wrote: post #418

Earlier quoted context omitted.

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…

> Software wants to be free. I feel like I'm in a time warp and we're back in 1993 or so on /. Software doesn't want anything and the people claim that technological progress is always good dream themselves to be the beneficiaries of that progress regardless of the effects on others, even if those are negative. As for the intentional limits on technological progress: there are so many examples of this that I wonder w…

I was one year old in 1993, so I'll defer to you on the meaning of this expression [0], but it sounds like you were on the opposite side of its ideological argument. How did that work out for you? Thirty years later, I'm not sure it's a position I'd want to brag about taking, considering the tremendous success and net positive impact of the Internet (despite its many flaws). Although, based on this Wikipedia article, I can see how it's a sort of Rorschach test that naive libertarians and optimistic statists could each interpret favorably according to their own bias.

[0] https://en.wikipedia.org/wiki/Information_wants_to_be_free

Re: ChatGPT Plugins

#850

Post by JCharante »

jasondigitized wrote: post #500
JCharante wrote: post #166

A first party version of apps that have been built with langchain is great but I'm dissapointed to not see Jira here yet. I have been playing around with GPT-4 parsing plaintext tickets and it is amazing what it does with the proper amount of context. It can draft tickets, familiarize itself with your stack by knowing all the tickets, understand the relationship between blockers, tell you why tickets are being blocke…

Tell me more. Are you feeding it a epic and all stories and subtasks? What are your prompts?

I gave it a paragraph "hiring" GPT-4 and explaining our mission. Then a sentence overview of our two projects (api and app) as well as a description of similar apps and how we're different. Then I have about 12 tickets written in plaintext like this:

Issue ID: GD-012 Type: Task Title: [api] Migrate to TRPC from express/rest Assignee: John Status: In Progress --Description Beginning-- --Description End--

Because the outputs are really long, here's an example of my interactions with Dave (the name I gave to GPT-4). There's also emails Dave has created to fictional stakeholders but that's too high up. Right now the problem I'm having is that sometimes Dave can remember the issue tracker state but when trying to output (so that I can store it) it can't produce a long enough output (now, it worked before when I had 6 tickets). If I were to cram everything into 1 prompt then it would probably work, but a better solution is to use langchain and a document loader for issues.

I believe that if I was able to vectorize the codebase so that if could search for relavent portions of code (at work a lot of our tickets were "update this endpoint to handle case X, we did it to this other endpoint 6 months ago (link to PR)) and have a proper store of issues then it could be powerful.

Creating epics:

https://poe.com/s/Qu62LtlV2yKGZXlXTTS1

Explaining blockers:

https://poe.com/s/vnE0SsI3e55WT1t6fkNW

Creating tickets with a recommended checklist of tasks:

https://poe.com/s/SJ3RPF7ecHSYEBJKS76z

Post reply on HN