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

GPT-3.5 Turbo fine-tuning and API updates

openai.com

Post reply on HN
Print view View original

201–210 of 244 posts

Re: GPT-3.5 Turbo fine-tuning and API updates

#201

Post by matheusmoreira »

sheepscreek wrote: post #119
bennyschmidt wrote: post #114

GPT 3.5 is so bad it's useless to me - for writing it's too repetitive of the same kind of jargon, for coding it's wrong way too often. The NLP is also worse, I have to be more explicit. It's just an average chat bot IMO. GPT 4 @ $20/mo. is significantly better at everything, I use it for doing stuff in Angular lol - when you have an AI explaining the why behind everything, this over-engineered mess of a framework st…

> forget the phony ethics, and focus on the best version of this technology I’ve experimented a lot between the censored and uncensored versions of Llama 2. Based on this, I’ve concluded that fine-tuning for political correctness and ethics negatively affects all answers. They become repetitive and washed out.

I hope this technology keeps improving to the point we can run it on our own machines. It's too good to be censored.

Re: GPT-3.5 Turbo fine-tuning and API updates

#202

Post by textcortex »

skerit wrote: post #196
bambax wrote: post #195

Could someone explain in simple terms exactly what fine-tuning does? Does it show the model how to answer questions, or does it give it new information, or both? Is there a way to restrict answers to the fine-tuned data? For example, if one would want to use an LLM to answer questions regarding a large, private knowledge base, would it make sense to fine-tune a model on this knowledge base? If yes, how does one reduc…

> For example, if one would want to use an LLM to answer questions regarding a large, private knowledge base, would it make sense to fine-tune a model on this knowledge base? I initially also thought this would be one of the best use cases for fine-tuning (teaching the model new data), but I've seen quite a few people say fine-tuning should not be used to teach the model new data, but more like new formatting and sty…

Most probably they are doing something called prompt tuning. This creates a small ai model that adds virtual tokens to prompt before passing to original model: https://developer.nvidia.com/blog/an-introduction-to-large-l...

Re: GPT-3.5 Turbo fine-tuning and API updates

#203

Post by matheusmoreira »

Havoc wrote: post #104
htrp wrote: post #62

Earlier quoted context omitted.

This one seems to be a deal-breaker, if you already know what types of language you want, why would you want openai moderating your parameter tuning set.

Why do you care at all, let alone "dealbreaker". You need a model specifically fine tuned towards something dangerous?

I want a "pure" model trained with every piece of information humanity has ever created. Absolutely no exceptions of any kind and especially none of this arbitrary political "fine tuning". Calling it "dangerous" only makes me want it more.

Re: GPT-3.5 Turbo fine-tuning and API updates

#204

Post by erik1332 »

matheusmoreira wrote: post #200
bennyschmidt wrote: post #114

GPT 3.5 is so bad it's useless to me - for writing it's too repetitive of the same kind of jargon, for coding it's wrong way too often. The NLP is also worse, I have to be more explicit. It's just an average chat bot IMO. GPT 4 @ $20/mo. is significantly better at everything, I use it for doing stuff in Angular lol - when you have an AI explaining the why behind everything, this over-engineered mess of a framework st…

I wish I could point the AI at huge GitHub codebases and have it explain the whole thing to me. Would make contributing to open source software so much easier.

There is a GTP-4 plugin available for this purpose. I have not tested it myself, but it may be worth trying out?

Re: GPT-3.5 Turbo fine-tuning and API updates

#205

Post by weird-eye-issue »

menzoic wrote: post #115
bennyschmidt wrote: post #114

GPT 3.5 is so bad it's useless to me - for writing it's too repetitive of the same kind of jargon, for coding it's wrong way too often. The NLP is also worse, I have to be more explicit. It's just an average chat bot IMO. GPT 4 @ $20/mo. is significantly better at everything, I use it for doing stuff in Angular lol - when you have an AI explaining the why behind everything, this over-engineered mess of a framework st…

Use code interpreter to upload your files and prompt it to ask you a serires of questions to know what to do next

Uploading a file to Code Interpreter does not magically increase the prompt context length. It will just read in part of the file or write code that operates on the file, depending on your prompt

Re: GPT-3.5 Turbo fine-tuning and API updates

#206

Post by davedx »

danielbln wrote: post #11
minimaxir wrote: post #4

Generating from a finetuned GPT 3.5 Turbo is 8x the cost of generating from the base model, so you really have to be in the “reduce prompt size by 90%” bucket they mention to get cost effectiveness out of it.

If you do a lot of retrieval augmentation, then the 8x cost might still be cheaper than burning a lot of tokens on injected context.

That doesn't make sense - if you're doing retrieval augmentation, then every prompt will be different depending on the query, right? So you still need to burn those tokens.

Re: GPT-3.5 Turbo fine-tuning and API updates

#207

Post by weird-eye-issue »

inglor wrote: post #12
samstave wrote: post #2

ELI5 what this means and impact?

ChatGPT but instead of learning from the internet and then producing text, learning from the internet + and then producing text. It's an announcement about the availability of a feature to do that. The article doesn't mention the biggest issue with fine-tuned models though - cost.

Well you are wrong on a couple levels

This is not really meant to teach it new information. It is meant to instruct it how to respond to well defined tasks

And secondly the cost is already clearly explained

Re: GPT-3.5 Turbo fine-tuning and API updates

#208

Post by gsin_ »

bennyschmidt wrote: post #114

GPT 3.5 is so bad it's useless to me - for writing it's too repetitive of the same kind of jargon, for coding it's wrong way too often. The NLP is also worse, I have to be more explicit. It's just an average chat bot IMO. GPT 4 @ $20/mo. is significantly better at everything, I use it for doing stuff in Angular lol - when you have an AI explaining the why behind everything, this over-engineered mess of a framework st…

For your use case of troubleshooting assistant are you pasting code into ChatGPT or using something like cursor.so ?

Re: GPT-3.5 Turbo fine-tuning and API updates

#209

Post by danielbln »

davedx wrote: post #206
danielbln wrote: post #11

Earlier quoted context omitted.

If you do a lot of retrieval augmentation, then the 8x cost might still be cheaper than burning a lot of tokens on injected context.

That doesn't make sense - if you're doing retrieval augmentation, then every prompt will be different depending on the query, right? So you still need to burn those tokens.

You can persist the knowledge you would normally retrieve dynamically and inject into the context at runtime via finetuning directly into the model weights. This means you won't have to pull in a glob of additional data with every prompt, but only need to push the query through, which can be answered by the data persisted in the weights.

However, as others have pointed out, you lose the ability to reference sources reliably and the output is much more prone to hallucination.

Re: GPT-3.5 Turbo fine-tuning and API updates

#210

Post by davedx »

danielbln wrote: post #209
davedx wrote: post #206

Earlier quoted context omitted.

That doesn't make sense - if you're doing retrieval augmentation, then every prompt will be different depending on the query, right? So you still need to burn those tokens.

You can persist the knowledge you would normally retrieve dynamically and inject into the context at runtime via finetuning directly into the model weights. This means you won't have to pull in a glob of additional data with every prompt, but only need to push the query through, which can be answered by the data persisted in the weights. However, as others have pointed out, you lose the ability to reference sources r…

Ahh understood, thank you.
Post reply on HN