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

New models and developer products

openai.com

Post reply on HN
Print view View original

381–390 of 561 posts

Re: New models and developer products

#381

Post by unshavedyak »

nmfisher wrote: post #345
jack_riminton wrote: post #253

For all the naysayers in the comments, the elephant in the room that no one quite wants to admit, is that GPT4 is still far better than everything else out there

I cancelled my GPT4 subscription because I found Claude more useful for code and Qwen for Chinese language tasks. It might be better on average but I don’t think it’s better for every task. All the others are only going to get better too.

Can you go into depth? I’ve used ChatGPT Pro and Phind extensively, didn’t know about Claude and code. Curious to give it a try

Re: New models and developer products

#382

Post by Michelangelo11 »

simonw wrote: post #241

I just released a new version of my LLM CLI tool with support for the new GPT-4 Turbo model: https://llm.datasette.io/en/stable/changelog.html#v0-12 You can install it like this: pipx install llm Then set an API key: llm keys set openai Then run a prompt through GPT-4 Turbo like this: llm -m gpt-4-turbo "Ten great names for a pet walrus" # Or a shortcut: llm -m 4t "Ten great names for a pet walrus" Here's a one-liner…

Jesus. Yeah, considering the input size, this is a pretty good sign that the 128k context window is working decently well.

Re: New models and developer products

#383

Post by qingcharles »

nmfisher wrote: post #345
jack_riminton wrote: post #253

For all the naysayers in the comments, the elephant in the room that no one quite wants to admit, is that GPT4 is still far better than everything else out there

I cancelled my GPT4 subscription because I found Claude more useful for code and Qwen for Chinese language tasks. It might be better on average but I don’t think it’s better for every task. All the others are only going to get better too.

Claude is superior for me on writing summaries of large documents.

Re: New models and developer products

#384

Post by nmfisher »

unshavedyak wrote: post #381
nmfisher wrote: post #345

Earlier quoted context omitted.

I cancelled my GPT4 subscription because I found Claude more useful for code and Qwen for Chinese language tasks. It might be better on average but I don’t think it’s better for every task. All the others are only going to get better too.

Can you go into depth? I’ve used ChatGPT Pro and Phind extensively, didn’t know about Claude and code. Curious to give it a try

I generally use it for boilerplate tasks like “here’s some code, write unit tests” or “here’s a JSON object, write a model class and parser function”.

Claude is significantly faster, so even if it requires a couple more prompt iterations than GPT4, I still get the result I need earlier than with GPT4.

GPT4 also recently developed this annoying tendency to only give you one or two examples of what you asked for, then say “you can write the rest on your own based on this template”. I can’t overstate how annoying this was.

Re: New models and developer products

#385

Post by spookie »

w-m wrote: post #284
throw2321 wrote: post #268

Earlier quoted context omitted.

I've been thinking about this for a while now, wrt two points: 1. This will be the end of traditional SWEs and the rise of the age of debuggers, human debuggers who spend their days setting up breakpoints and figuring bugs in a sea of LLM generated code. 2. Hiring will switch from using Leetcode questions to "pull out your debugger and figure out what's wrong with this code".

What makes you think the LLM couldn’t run a debugging session from the content of a JIRA ticket and the whole code base + documentation?

If the codebase is anything more than a simple Python project... I don't think that'll happen.

It just doesn't scale that well. Hell, GPT-4 can't make sense of my own projects.

Re: New models and developer products

#386

Post by infecto »

MagicMoonlight wrote: post #239
saliagato wrote: post #105

You can now [1] pay from $2 to $3 million to pretrain custom gpt-n model. This has gone unnoticed but seems really neat. Provided that a start-up has enough money spend on that, it would certainly give competitive advantage. [1] https://openai.com/form/custom-models Edit: forgot to put the link

Well it won’t because they’ll use the model you paid for and take your customers.

Do you have proof or are you just throwing baseless accusations out there?

Re: New models and developer products

#387

Post by gk1 »

danielbln wrote: post #149
m3kw9 wrote: post #141

Earlier quoted context omitted.

How does this absolve vectordbs

It doesn't, but semantic search is a lot less relevant if you can squeeze 350 pages of text into the context.

Besides the cost factor, stuffing the context window can actually make the results worse. https://www.pinecone.io/blog/why-use-retrieval-instead-of-la...

Re: New models and developer products

#388

Post by m3kw9 »

oezi wrote: post #242
dragonwriter wrote: post #150

Earlier quoted context omitted.

If you are using OpenAI, the new Assistants API looks like itnwill handle internally what you used to handle externally with a vector DB for RAG (and for some things, GPT-4-Turbo’s 128k context window will make it unnecessary entirely.) There are some other uses for Vector DBs than RAG for LLMs, and there are reasons people might use non-OpenAI LLMs with RAG, so there is still a role for VectorDBs, but it shrunk a lo…

OpenAI is still way too expensive to run a corporate knowledge base on top

It’s more reliable than chatpdfs that relies on vector search. With vector db all you are doing is doing a fuzzy search and then sending in that relevant portion near that text and send it to a LLM model as part of a prompt. It misses info.

Re: New models and developer products

#389

Post by speak_plainly »

abound wrote: post #262
speak_plainly wrote: post #256

Can we get version of ChatGPT Plus where your data is confidential and not used for training, like a light version of ChatGPT Enterprise for individuals?

That exists as a setting, but that same, single setting also disables your web chat history.

That's great, thanks!

Re: New models and developer products

#390

Post by layer8 »

famouswaffles wrote: post #322
layer8 wrote: post #198

The TTS seems really nice, though still relatively expensive, and probably limited to English (?). I can’t wait until that level of TTS will become available basically for free, and/or self-hosted, with multi-language support, and ubiquitous on mobile and desktop.

It's not limited to English. The model at least. Doubt the API will be too. Expensive ? Compared to what? Eleven labs costs an arm and a leg in comparison.

Compared to iOS' built-in TTS, which is free (though of course not comparable in quality).
Post reply on HN