News for hackers. Stuff that matters.
Re:Show HN: LLMs can generate valid JSON 100% of the time by mattigames on Monday August 14, 2023 @07:21PM (#37128113)
It's not like humans are particularly good at distinguishing truth from lies.
Re:Show HN: LLMs can generate valid JSON 100% of the time by quickthrower2 on Monday August 14, 2023 @07:33PM (#37128203)
The word "lie" is probably too anthropic here. I should have just said "made up". There is no intent to lie. And the model isn't try to self-fact-check anyway. (Maybe some do). But if they do they are probably bad at it at the moment, at least from my experience of GPT3.5 (not used 4 much).
Re:Show HN: LLMs can generate valid JSON 100% of the time by coder543 on Monday August 14, 2023 @07:58PM (#37128396)
> at least from my experience of GPT3.5 (not used 4 much).

And 4 is tremendously better than 3.5, in my own experience. Not perfect, but actually useful.

Re:Show HN: LLMs can generate valid JSON 100% of the time by quickthrower2 on Monday August 14, 2023 @08:25PM (#37128586)
Can anyone recommend a good, and trusted UI so I can use it via the API? I don't want to pay monthly for it, but would be nice to use occasionally. I keep meaning to do this!
Re:Show HN: LLMs can generate valid JSON 100% of the time by selcuka on Monday August 14, 2023 @09:23PM (#37129024)
OpenAI has its own playground where you can test all models (I believe GPT-4 is not available to everyone yet):

https://platform.openai.com/playground

Monthly subscription is only for ChatGPT. When you use the APIs you pay per token.

Re:Show HN: LLMs can generate valid JSON 100% of the time by coder543 on Monday August 14, 2023 @11:25PM (#37129803)
> I believe GPT-4 is not available to everyone yet

I still don't have access, except through the regular ChatGPT interface, which is mildly annoying. It would be interesting to experiment with the API.

Re:Show HN: LLMs can generate valid JSON 100% of the time by dilawar on Monday August 14, 2023 @10:08PM (#37129324)
"Its a human nature to mislead others, sometimes knowingly." I read this line in an anthropology book. A similarly non-cynical approach towards your fellow is "trust but verify".