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

Function calling and other API updates

openai.com

Post reply on HN
Print view View original

91–100 of 174 posts

Re: Function calling and other API updates

#91

Post by ilaksh »

anotherpaulg wrote: post #86
ilaksh wrote: post #81

Earlier quoted context omitted.

What I'm thinking is to give it a function called replaceAll that just replaces text, and another one called insertAfter. Maybe also replaceBetween.

Absolutely! I will certainly be experimenting with the new functions as you suggest. One thing which I haven't seen discussed elsewhere is the tension between the output format and the underlying task. When I ask GPT to use a simple, natural output format it does *better* at the actual code editing task. If I ask it to output using a more technical format like `diff -c` or heavily structured json formats... it "gets…

My guess is the new function training might overall slightly take away from the capacity for other types of reasoning, since it's a fixed capacity. But hopefully significantly less impact than including the instructions on the fly, since it's mostly baked in to the model now which should be a more efficient encoding.

Re: Function calling and other API updates

#92

Post by LelouBil »

anotherpaulg wrote: post #68

I've been spending a lot of time figuring out how to make these GPT models successful at *editing* existing code. This is much more difficult than having them write brand new code. So far, gpt-4 has been significantly better at editing code than gpt-3.5-turbo. This is for two reasons (which I previously discussed here [1]): 1. GPT-4's bigger context window lets it understand and edit larger codebases. The new 16k win…

Speaking about editing, is there a name and/or an explanations for the behaviour that LLMs have sometimes of saying they did something when they don't ?

Like :

Me : Fix this code

ChatGPT : edits it but incorrectly

Me: no, do it like .....

ChatGPT: Okay, I edited it like ... Sends back the same code as last time

Is it linked to the fact that these LLMs never or very rarely refuse a prompts even if it's something they can't do ?

Re: Function calling and other API updates

#93

Post by lukaslezevicius »

andybak wrote: post #80
jumploops wrote: post #14

This seems like a direct result of Plugins not hitting PMF -- rather than give API developers access to Plugins, give them the underpinnings to build Plugin-like experiences. Love it!

I've forgotten what pmf means from the last time someone used it and someone else explained it. (Can we please all lighten up on the acronyms a touch?)

Product market fit.

Re: Function calling and other API updates

#94

Post by esafak »

theshrike79 wrote: post #72
hackernewds wrote: post #21

Earlier quoted context omitted.

An "average" person is not someone who knows how to call an API. Perhaps only on HN

"AI" as we know it is hardly 6 months old now, just wait a while and it'll be grandma accessible.

You exaggerate a bit! Machine learning and language models have been around for decades. OpenAI itself has been around since 2015.

Re: Function calling and other API updates

#95

Post by andybak »

lukaslezevicius wrote: post #93
andybak wrote: post #80

Earlier quoted context omitted.

I've forgotten what pmf means from the last time someone used it and someone else explained it. (Can we please all lighten up on the acronyms a touch?)

Product market fit.

I can see why my brain refuses to hold on to that one.

Re: Function calling and other API updates

#96

Post by alexp7 »

minimaxir wrote: post #7

The big feature here is the function calls, as this is effectively a replacement for the "Tools" feature of Agents popularized by LangChain, except in theory much more efficient since it may not require an extra call to the API. In the case of LangChain which selects Tools and their functional outputs through JSON Markdown shennanigans (which often fails and causes ParsingErrors), this variant of ChatGPT appears to b…

There is also an alternative approach for running code with ChatGPT, the way Nekton(https://nekton.ai) does it. It will use ChatGPT to generate typescript code code, and then just run it in the cloud.

In the end you get similar result - AI generated automation, but you have an option to review what the code will actually do before running it.

Re: Function calling and other API updates

#97

Post by avereveard »

com2kid wrote: post #12

GPT3.5 has been undergoing constant improvements, this price decrease (and context length increase) is great news! The main problem I see with people using GPT3.5 is they try and ask it to "write a short story about aliens" and then they get back a crap boring response that sounds like it was written by an AI that was asleep at the wheel. Good creative prompts are long and detailed, and to get the best results you re…

> Good creative prompts are long and detailed

They don't need to be tho. You can try shotgunning in (generate 100 titles about a novel around aliens, after the gen 'pick the one most likely to resonate to a X audience, explain why')

Or you can let AI drive itself interactively (ask yourself 20 question about how to write creative alien stories, and answer yourself)

Or you can process in spirals (generate a setting for an alien story, wait answer, generate 3 protagonista and one antagonist, wait, generate motives and relationships for each of them, wait, generate a backstory, wait, then you ask for the novel)

The point is letting the ai do the work. You can always "rewrite it with more drama and some comedic relief" afterward to fix tonal issues.

Re: Function calling and other API updates

#98

Post by dragonwriter »

MuffinFlavored wrote: post #82
naiv wrote: post #70

Earlier quoted context omitted.

Every api should have its own validation so I don't even see this as a problem. What is returned from openai should be treated like any other user input.

> Every api should have its own validation so I don't even see this as a problem. No. I'm saying, little by little people will rely on OpenAI hypothetically for more and more. How long until they are calling POST /credit/customer/bank/account and it just randomly goofs the ID/numbers? A "human" may or may not have made that mistake, where an LLM will never be a 100% perfect trustable entity by design (aka, hallucinat…

> A “human” may or may not have made that mistake, where an LLM will never be a 100% perfect trustable entity by design (aka, hallucinations).

This is equally true if you swap “human” and “LLM”. Humans, too, are fallible by design, and LLMs (except maybe with exactly fixed input and zero temperature) are generally not guaranteed to make or not make any given error.

Humans are more diverse both across instances and for the same instance at different times (because they have, to treat them as analogous systems [0], continuity with a very large multimodal context windows.) But that actually makes humans less reliable and predictable, not more, than LLMs.

[0] which is probably inaccurate, but...

Re: Function calling and other API updates

#99

Post by tedsanders »

alpark3 wrote: post #89

I wonder how much of these changes are pushed by the local LLM shift we've seen recently. I would've expected them to totally focus on GPT-4 updates, but it's nice that we're getting 3.5 improvements. It's pretty clear that there's a large demand for much cheaper, if weaker LLMs. I'll need to test the "more reliable steerability via the system message" feature, but GPT-3.5's largely monotonic tone and lack of respons…

Describing functions to GPT still costs extra tokens, unfortunately.

Re: Function calling and other API updates

#100

Post by 037 »

weinzierl wrote: post #53

16k context sounds exciting. The day I can throw a whole book at it and ask it arbitrary questions about it will be great. With 16k we are getting into full article realm and that is already incredibly useful. Is there any open model with a similar context length? [I'm not talking about the dubious for long context fine-tuned LLaMA variants, I mean the real thing.]

Not open, but with Anthropic the limit is 100k now https://news.ycombinator.com/item?id=35904773
Post reply on HN