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

OpenAI delays launch of custom GPT store until early 2024

axios.com

Post reply on HN
Print view View original

51–60 of 69 posts

Re: OpenAI delays launch of custom GPT store until early 2024

#51

Post by Solvency »

webappguy wrote: post #46
NameError wrote: post #5

The release of plugins was underwhelming for a lot of users, I wonder if they're worried about the same thing happening again. I had fun making a plugin when they were first announced but the developer experience was clunky and frustrating, and there was a lot of confusion around how the plugin store actually worked. I haven't made the time to convert my plugin into a GPT but I'm planning to, hopefully it'll be a bit…

As far as UX, and a product, chatGPT is terrible! Astounding and blows my mind for a 80+b dollar company. The model and tech (and team) is that value of course, but how can't they at the very most basic level, clean up the 'sidebar'. Prompts search and GPT labelling. Even when they had the plugins, most ppl didn't know you had to click on the GPT4 button to revial, because why would they...nothing indicated to (like…

And just imagine the outrageously overwrought, self-flagellating, beard-stroking, sophomoric, herculean UX interview process they torture designers with just to make...that.

Re: OpenAI delays launch of custom GPT store until early 2024

#53

Post by faizshah »

webappguy wrote: post #46
NameError wrote: post #5

The release of plugins was underwhelming for a lot of users, I wonder if they're worried about the same thing happening again. I had fun making a plugin when they were first announced but the developer experience was clunky and frustrating, and there was a lot of confusion around how the plugin store actually worked. I haven't made the time to convert my plugin into a GPT but I'm planning to, hopefully it'll be a bit…

As far as UX, and a product, chatGPT is terrible! Astounding and blows my mind for a 80+b dollar company. The model and tech (and team) is that value of course, but how can't they at the very most basic level, clean up the 'sidebar'. Prompts search and GPT labelling. Even when they had the plugins, most ppl didn't know you had to click on the GPT4 button to revial, because why would they...nothing indicated to (like…

I think they will end up buying Cohere, Cohere has a great product team and is an obvious fit.

Re: OpenAI delays launch of custom GPT store until early 2024

#54

Post by namibj »

morph123 wrote: post #25

Still dont understand why anyone would "pay" for this. The default model will probably be better in pretty much all cases. I guess if someone randomly has some sort of esoteric knowledge? Seems very limited.

ArxivXplorer works fairly well all considered... Bypasses the PDF and exposes math in a better format to the LLM.

Re: OpenAI delays launch of custom GPT store until early 2024

#55

Post by ShamelessC »

morph123 wrote: post #31
andybak wrote: post #30

Earlier quoted context omitted.

Not sure how much you've used custom GPTs. They are currently flawed and buggy but I think they hold promise. They combine 3 things: 1. A custom initial prompt (yeah - you can paste this in every time and keep a personal database of special purpose prompts - but it rather kills the convenience and utility) 2. A JSON description of one or more APIs that can be used (not just for retrieveal of information - but potenti…

I guess. I assume the OpenAI vision, in the short term, is for there to be a beefy LLM on top that can call the correct sub LLMs that have more bespoke knowledge about random things, and sort of orchestrate an answer based on that. Not sure why OpenAI feels the need to pay people for this though, I guess to incentivize use?

They all use a beefy LLM though.

Re: OpenAI delays launch of custom GPT store until early 2024

#59

Post by chatmasta »

webappguy wrote: post #46
NameError wrote: post #5

The release of plugins was underwhelming for a lot of users, I wonder if they're worried about the same thing happening again. I had fun making a plugin when they were first announced but the developer experience was clunky and frustrating, and there was a lot of confusion around how the plugin store actually worked. I haven't made the time to convert my plugin into a GPT but I'm planning to, hopefully it'll be a bit…

As far as UX, and a product, chatGPT is terrible! Astounding and blows my mind for a 80+b dollar company. The model and tech (and team) is that value of course, but how can't they at the very most basic level, clean up the 'sidebar'. Prompts search and GPT labelling. Even when they had the plugins, most ppl didn't know you had to click on the GPT4 button to revial, because why would they...nothing indicated to (like…

This says a lot more about the state of the frontend ecosystem than it does about the OpenAI dev team. The complexity has gotten absurdly out of control.

It's really quite ironic that on one hand, we've got a company on the cusp of developing a superintelligence, and a bunch of open source models lagging not too far behind. But on the other hand, you've gotta install it all with Python - and good luck, because nobody in the ecosystem is pinning dependencies and you're gonna have to re-install the thing every time you run it.

And then on the frontend, you've got the team responsible for creating the interface to the super intelligence. They've actually done a decent job thus far, but it's slow development and disconnected from more ambitious scaling ideas.

Re: OpenAI delays launch of custom GPT store until early 2024

#60

Post by Tostino »

nxobject wrote: post #36
Tostino wrote: post #21

Earlier quoted context omitted.

Honestly, I am excited for people to re-implement the API for this using open models because of this. Maybe let the API stabilize a little, and i'm sure some implementations will pop-up.

What's the state of open models, though? I know that OpenAI's secret sauce is paying $$$ for access to private corpora, like the AP's archive, and I wonder how much the different levels of access to training data are reflected in any divide between open and commercial models, especially in different use cases like fact retrieval and synthesis. (I've gotten too reliant on ChatGPT to satisfy my curiosity re: random que…

Heh, so it totally depends on the use case.

I use GPT4 constantly to chat through issues I am working on and get different perspectives. I cannot do that with local models.

On the other hand, I have been processing a ton of text transcripts with a fine tuned llama2 13b model i've been working on, and for the tasks I have fine-tuned on, my local model is producing better results than GPT4, often taking a task that I had to do in multiple steps with GPT4, and being able to complete it in a single shot.

I can run my local model through vLLM on my workstation at around the same tokens/sec as I can spend maxing out my API limits with GPT3.5-turbo (~$20/hr) while running on 2x 3090's. I'm hitting the vLLM (OpenAI clone) chat/completions endpoint. My model implements the HF chat_templates feature, and I worked on adding support for that to vLLM: https://github.com/vllm-project/vllm/pull/1756 (llama.cpp is talking about adding support for it too) so I could easily swap out my model in my data pipeline in place of GPT3.5/GPT4, and I wouldn't have to keep maintaining that code on my side.

So, with these transcripts I've been:

  - Creating YAML knowledge graphs
  - Summaries
  - Fixing transcription issues
  - Creating QA pairs
  - Identifying sections related to promoting a product or brand
  - Grading the output that it had generated on accuracy
So...it depends on your use case.
Post reply on HN