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

141–150 of 258 posts

Re: Native JSON Output from GPT-4

#141

Post by swyx »

moneywoes wrote: post #97
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

i mean hopefully its relevant content to the discussion, i hope enough pple know me here by now that i fully participate in The Discourse rather than just being here to cynically plug my stuff. i had a 1.5 hr convo with simon willison and other well known AI tinkerers on this exact thing, and so I shared it, making the most out of their time that they chose to share with me.

Re: Native JSON Output from GPT-4

#143

Post by swyx »

TeMPOraL wrote: post #108
moneywoes wrote: post #97

Earlier quoted context omitted.

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

They're the only one commenter on HN I noticed keeps writing "smol" instead of "small", and is associated with projects with "smol" in their name. Surely I'm not the only one who missed it being a meme around 2015 or sth., and finds this word/use jarring - and therefore very attention-grabbing? Wonder how much that helps with marketing. This is meant with no negative intentions. It's just that 'swyx was, in my mind,…

and fun fact i used to work at Temporal too heheh.

Re: Native JSON Output from GPT-4

#144

Post by bel423 »

Did people really struggle with getting JSON outputs from GPT4. You can literally do it zero shot by just saying match this typescript type.

GPT3.5 would output perfect JSON with a single example.

I have no idea why people are talking about this like it’s a new development.

Re: Native JSON Output from GPT-4

#145

Post by bel423 »

ignite wrote: post #106
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…

> You just append ‘reply in json with this format’ and it does a really good job. It does an ok job. Except when it doesn't. Definitely misses a lot of the time, sometimes on prompts that succeeded on previous runs.

It literally does it everytime perfectly. I remember I put together an entire system that would validate the JSON against a zod schema and use reflection to fix it and it literally never gets triggered because GPT3.5-turbo always does it right the first time.

Re: Native JSON Output from GPT-4

#146

Post by swyx »

runeb wrote: post #126

The way openai implemented this is really clever, beyond how neat the plugin architecture is, as it lets them peek one layer inside your internal API surface and can infer what you intend to do with the LLM output. Collecting some good data here.

huh, i never thought of it that way. i thought openai pinky swears not to train on our data tho

Re: Native JSON Output from GPT-4

#147

Post by brolumir »

bel423 wrote: post #144

Did people really struggle with getting JSON outputs from GPT4. You can literally do it zero shot by just saying match this typescript type. GPT3.5 would output perfect JSON with a single example. I have no idea why people are talking about this like it’s a new development.

Unfortunately, in practice that works only most of the time. At least in our experience (and the article says something similar) sometimes ChatGPT would return something completely different when JSON-formatted response would be expected.

Re: Native JSON Output from GPT-4

#148

Post by killingtime74 »

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…

Who is Simon Willison? Is he big in AI?

Re: Native JSON Output from GPT-4

#149

Post by bel423 »

ztratar wrote: post #77
cwxm wrote: post #74

Earlier quoted context omitted.

even with gpt 4, it hallucinates enough that it’s not reliable, forgetting to open/close brackets and quotes. This sounds like it’d be a big improvement.

Nah, this was solved by most teams a while ago.

I feel like I’m taking crazy pills with the amount of people saying this is game changing.

Did they not even try asking gpt to format the output as json?

Re: Native JSON Output from GPT-4

#150

Post by swyx »

killingtime74 wrote: post #148
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…

Who is Simon Willison? Is he big in AI?

formerly cocreator of Django, now Datasette, but pretty much the top writer/hacker on HN making AI topics accessible to engineers https://hn.algolia.com/?dateRange=pastYear&page=0&prefix=tru...
Post reply on HN