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

Native JSON Output from GPT-4

yonom.substack.com

Post reply on HN
Print view View original

91–100 of 258 posts

Re: Native JSON Output from GPT-4

#91

Post by reallymental »

jonplackett wrote: post #65
swyx wrote: post #19

i think people are underestimating the potential here for agents building - it is now a lot easier for GPT4 to call other models, or itself. while i was taking notes for our emergency pod yesterday ( https://www.latent.space/p/function-agents ) we had this interesting debate with Simon Willison on just how many functions will be supplied to this API. Simon thinks it will be "deep" rather than "wide" - eg a few functi…

It was already quite easy to get GPT-4 to output json. You just append ‘reply in json with this format’ and it does a really good job. GPT-3.5 was very haphazard though and needs extensive babysitting and reminding, so if this makes gpt3 better then it’s useful - it does have an annoying disclaimer though that ‘it may not reply with valid json’ so we’ll still have to do some sense checks into he output. I have been u…

Is there any publicly available resource replicate your work? I would love to just find the right kind of "incantation" for the gpt-3.5-t or gpt-4 to output a meaningful story arc etc.

Any examples of your work would be greatly helpful as well!

Re: Native JSON Output from GPT-4

#92

Post by TeMPOraL »

nasir wrote: post #67
irthomasthomas wrote: post #50

It's a shame they couldn't use yaml, instead. I compared them and yaml uses about 20% fewer tokens. However, I can understand accuracy, derived from frequency, being more important than token budget.

Its a lot more straightforward to use JSON programmatically than YAML.

It really shouldn't be, though. I.e. not unless you're parsing or emitting it ad-hoc, for example by assuming that an expression like:

  "{" + $someKey + ":" + $someValue + "}"
produces a valid JSON. It does - sometimes - and then it's indeed easier to work with. It'll also blow up in your face. Using JSON the right way - via a proper parser and serializer - should be identical to using YAML or any other equivalent format.

Re: Native JSON Output from GPT-4

#93

Post by loughnane »

Just this morning I wrote a JSON object. I told GPT to turn it into a schema. I tweaked that and then gave a list of terms for which I wanted GPT to populate the schema accordingly.

It worked pretty well without any functions, but I did feel like I was missing something because I was ready to be explicit and there wasn’t any way for me to tell that to GPT.

I look forward to trying this out.

Re: Native JSON Output from GPT-4

#94

Post by londons_explore »

Tostino wrote: post #64
ftxbro wrote: post #59

Earlier quoted context omitted.

> "you can now trivially make GPT4 decide whether to call itself again, or to proceed to the next stage." Does this mean the GPT-4 API is now publicly available, or is there still a waitlist? If there's a waitlist and you literally are not allowed to use it no matter how much you are willing to pay then it seems like it's hard to call that trivial.

Not GP, but it's still the latter...i've been (im)patiently waiting. From their blog post the other day: With these updates, we’ll be inviting many more people from the waitlist to try GPT-4 over the coming weeks, with the intent to remove the waitlist entirely with this model. Thank you to everyone who has been patiently waiting, we are excited to see what you build with GPT-4!

If you put contact info in your HN profile - especially an email address that matches one you use to login to openai, someone will probably give you access...

Anyone with access can share it with any other user via the 'invite to organisation' feature. Obviously that allows the invited person do requests billed to the inviter, but since most experiments are only a few cents that doesn't really matter much in practice.

Re: Native JSON Output from GPT-4

#95

Post by EGreg »

yonom wrote: post #55
EGreg wrote: post #47

Actually I'm looking to take GPT-4 output and create file formats like keynote presentations, or pptx. Is that currently possible with some tools?

I would recommend creating a simplified JSON schema for the slides (say, presentation is an array of slides, each slide has a title, body, optional image, optional diagram, each diagram is one of pie, table, ... Then use a library to generate the pptx file from the content generated.

Library? What library?

It seems to me that a Transformer should excel at Transforming, say, text into pptx or pdf or HTML with CSS etc.

Why don't they train it on that? So I don't have to sit there with manually written libraries. It can easily transform HTML to XML or text bullet points so why not the other formats?

Re: Native JSON Output from GPT-4

#96

Post by londons_explore »

lbeurerkellner wrote: post #53
behnamoh wrote: post #44

Earlier quoted context omitted.

What's the implication of this new change for Microsoft Guidance, LMQL, Langchain, etc.? It looks like much of their functionality (controlling model output) just became obsolete. Am I missing something?

If anything this removes a major roadblock for libraries/languages that want to employ LLM calls as a primitive, no? Although, I fear the vendor lock-in intensifies here, also given how restrictive and specific the Chat API. Either way, as part of the LMQL team, I am actually pretty excited about this, also with respect to what we want to build going forward. This makes language model programming much easier.

> Although, I fear the vendor lock-in intensifies here,

The openAI API is super simple - any other vendor is free to copy it, and I'm sure many will.

Re: Native JSON Output from GPT-4

#97

Post by moneywoes »

swyx wrote: post #19

i think people are underestimating the potential here for agents building - it is now a lot easier for GPT4 to call other models, or itself. while i was taking notes for our emergency pod yesterday ( https://www.latent.space/p/function-agents ) we had this interesting debate with Simon Willison on just how many functions will be supplied to this API. Simon thinks it will be "deep" rather than "wide" - eg a few functi…

Wow your brand is huge. Crazy growth. i wonder how much these subtle mentions on forums help

Re: Native JSON Output from GPT-4

#98

Post by stevenhuang »

EGreg wrote: post #47

Actually I'm looking to take GPT-4 output and create file formats like keynote presentations, or pptx. Is that currently possible with some tools?

apparently pandoc also supports pptx

so you can tell GPT4 to output markdown, then use pandoc to convert that markdown to pptx or pdf.

Re: Native JSON Output from GPT-4

#99

Post by SamPatt »

reallymental wrote: post #91
jonplackett wrote: post #65

Earlier quoted context omitted.

It was already quite easy to get GPT-4 to output json. You just append ‘reply in json with this format’ and it does a really good job. GPT-3.5 was very haphazard though and needs extensive babysitting and reminding, so if this makes gpt3 better then it’s useful - it does have an annoying disclaimer though that ‘it may not reply with valid json’ so we’ll still have to do some sense checks into he output. I have been u…

Is there any publicly available resource replicate your work? I would love to just find the right kind of "incantation" for the gpt-3.5-t or gpt-4 to output a meaningful story arc etc. Any examples of your work would be greatly helpful as well!

I'm not the person you're asking, but I built a site that allows you to generate fiction if you have an OpenAI API key. You can see the prompts sent in console, and it's all open source:

https://havewords.ai/

Re: Native JSON Output from GPT-4

#100

Post by rytill »

bradly wrote: post #82
jonplackett wrote: post #65

Earlier quoted context omitted.

It was already quite easy to get GPT-4 to output json. You just append ‘reply in json with this format’ and it does a really good job. GPT-3.5 was very haphazard though and needs extensive babysitting and reminding, so if this makes gpt3 better then it’s useful - it does have an annoying disclaimer though that ‘it may not reply with valid json’ so we’ll still have to do some sense checks into he output. I have been u…

I could not get GPT-4 to reliably not give some sort of text response, even if was just a simple "Sure" followed by the JSON.

Did you try using the API and providing a very clear system message followed by several examples that were pure JSON?
Post reply on HN