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

GPT-3 APIs are now in public beta

openai.com

Post reply on HN
Print view View original

131–140 of 163 posts

Re: GPT-3 APIs are now in public beta

#131

Post by 6gvONxR4sf7o »

Workaccount2 wrote: post #121
edouard-harris wrote: post #117

Earlier quoted context omitted.

I agree these capabilities can't really be suppressed in the long term. But, as with nuclear nonproliferation, there is safety value in lowering the diffusion coefficient of their spread to the point where policy and countermeasures may be able to catch up. From that perspective, OpenAI's gatekeeping contributes to this effort at the margin.

We aren't talking about nuclear weapons where you need extreme niche expertise and billion dollar labs to build one. We're talking about stopping the proliferation of binary blobs banged out by college kids on their laptops. Good luck.

We’re still not at the point where the larger language models can be banged out by college kids on their laptops. Maybe we’ll be there soon, but that’s a different point. And we want openai to hasten that future?

Re: GPT-3 APIs are now in public beta

#132

Post by thedorkknight »

warning26 wrote: post #4
friedman23 wrote: post #2

This is cool but I'm hesitant to invest any real amount of time building something on this. How do I know that if I build something massively successful they wont shut off my access and build a competitor?

Or change their TOS to effectively ban your product, as they did with AI Dungeon.

? I'm using it right now and it's fine

Re: GPT-3 APIs are now in public beta

#133

Post by stavros »

zitterbewegung wrote: post #118
stavros wrote: post #111

Earlier quoted context omitted.

Hmm, how do these compare to GPT-3 for dialog? One issue I have with GPT-3 is that it doesn't remember anything.

GPT-3 has you crafting a conversation while HuggingFace was much easier to use. Blenderbot v2 will have memory and I am looking towards replacing my version with Blenderbot v2.

Hm yeah, Blenderbot v2 does sound great, but as far as I can see, Huggingface doesn't support it yet.

Re: GPT-3 APIs are now in public beta

#134

Post by wayeq »

TulliusCicero wrote: post #10
fenomas wrote: post #3

Looks neat, but note that OpenAI is basically an App Store model - whatever you make with it cannot be shown to more than five people unless OpenAI has reviewed and explicitly approved your project. And their usage guidelines are pretty narrow - "open-ended chatbots" are explicitly disallowed, for example. > https://beta.openai.com/docs/going-live > https://beta.openai.com/docs/usage-guidelines/use-case-guide...

Yeah, it’s pretty disappointing given their name. More like ClosedAI am I rite guyz

got 'em

Re: GPT-3 APIs are now in public beta

#135

Post by xkapastel »

Workaccount2 wrote: post #121
edouard-harris wrote: post #117

Earlier quoted context omitted.

I agree these capabilities can't really be suppressed in the long term. But, as with nuclear nonproliferation, there is safety value in lowering the diffusion coefficient of their spread to the point where policy and countermeasures may be able to catch up. From that perspective, OpenAI's gatekeeping contributes to this effort at the margin.

We aren't talking about nuclear weapons where you need extreme niche expertise and billion dollar labs to build one. We're talking about stopping the proliferation of binary blobs banged out by college kids on their laptops. Good luck.

A model of GPT-3's scale is not going to be trained or run on a laptop. OpenAI's restrictions are significant because not many people can run a model that large.

Re: GPT-3 APIs are now in public beta

#136

Post by fguerraz »

Is it just me or is the example they take for summarization actually bad?

"Allison is excited to meet with New Horizon Manufacturing to discuss their photovoltaic window system."

should be

"Allison is excited to meet with New Horizon Manufacturing to discuss OUR photovoltaic window system."

Re: GPT-3 APIs are now in public beta

#137

Post by jonathanlb »

dave_sullivan wrote: post #82
fenomas wrote: post #3

Looks neat, but note that OpenAI is basically an App Store model - whatever you make with it cannot be shown to more than five people unless OpenAI has reviewed and explicitly approved your project. And their usage guidelines are pretty narrow - "open-ended chatbots" are explicitly disallowed, for example. > https://beta.openai.com/docs/going-live > https://beta.openai.com/docs/usage-guidelines/use-case-guide...

I don't know why anyone is still paying attention to Open AI's offerings. Use GPT Neo. Use Huggingfaces. Use colab or bare metal or any cloud provider. Open AI's offering is bringing literally nothing to the table that doesn't exist already. Their publications are good (albeit missing important details), but everyone working there was publishing anyway so it's not like this research wouldn't happen without Open AI ex…

> How full of yourself do you have to be to say something like, "Oh, we can't share this knowledge because it's too dangerous"

Not surprising considering the founders include Elon Musk and Sam Altman

Re: GPT-3 APIs are now in public beta

#138

Post by harpersealtako »

edouard-harris wrote: post #113
cbozeman wrote: post #86

Earlier quoted context omitted.

> "Oh, we can't share this knowledge because it's too dangerous" Every time I hear someone say this, I always think, "Dangerous... to whom ?"

(AI safety researcher here.) GPT-3's current level of accessibility is already dangerous, and quite broadly so. To focus on just one documented example, the model can out-of-the-box (i.e., without any fine tuning) be used for persuasion and influence operations at scale on social media. In fact, the feasibility of this has been verified in text generation experiments [1]. Here are a couple of examples taken from the…

I've always strongly disagreed with this particular threat model of AI safety. To me, the biggest threat of AI isn't autogenerated spammy fake news or social media posts (how much cheaper is it really than just hiring a 5-cent army to do that? Aren't there diminishing returns for doing this too much? Since this is basically inevitable isn't it a better idea to teach people not to believe stuff they read from unreliable strangers on the internet?).

Rather the biggest threat is centralization, where a single corporation (e.g. Microsoft, Google, Facebook, a single government agency) controls the AI, censors/limits it in places that are inconvenient to it and its profits, snoops on all communications with no regard for privacy, etc. OpenAI already does this, and they're quite clear and open about it.

And what I'm REALLY concerned about is AI companies like OpenAI building a cutting-edge AI, then lobbying governments to prevent anybody else from building one freely for the sake of "safety". AI safety researchers hired by AI companies have a clear conflict of interest here. I think that the ONLY way to make sure AI is safe is if it has 100% transparency, i.e. open source and freely available models that anybody can run and test themselves.

Re: GPT-3 APIs are now in public beta

#139

Post by vorpalhex »

gcoda wrote: post #14
vorpalhex wrote: post #11

Several clones of GPT-3 exist, a few successors that may be a bit better, and even a few leaks of gpt-3 itself.

I know about gpt-j, can you name worthy clones/alternatives?

gpt-neo is the one I would keep my eye on. https://github.com/EleutherAI/gpt-neo

Re: GPT-3 APIs are now in public beta

#140

Post by hollerith »

dave_sullivan wrote: post #82
fenomas wrote: post #3

Looks neat, but note that OpenAI is basically an App Store model - whatever you make with it cannot be shown to more than five people unless OpenAI has reviewed and explicitly approved your project. And their usage guidelines are pretty narrow - "open-ended chatbots" are explicitly disallowed, for example. > https://beta.openai.com/docs/going-live > https://beta.openai.com/docs/usage-guidelines/use-case-guide...

I don't know why anyone is still paying attention to Open AI's offerings. Use GPT Neo. Use Huggingfaces. Use colab or bare metal or any cloud provider. Open AI's offering is bringing literally nothing to the table that doesn't exist already. Their publications are good (albeit missing important details), but everyone working there was publishing anyway so it's not like this research wouldn't happen without Open AI ex…

>How full of yourself do you have to be to say something like, "Oh, we can't share this knowledge because it's too dangerous"

Were the decisionmakers in the US government also full of themselves for not publishing the knowledge of how to make a nuclear weapon?

Most knowledge is not dangerous, but please consider the possibility that some of the newer knowledge around machine learning might be dangerous to publish.

Post reply on HN