Hacker News Reader

Comment by kylebenzle | Hacker News Reader

Reading this article brought me no closer to understanding why people use these. From day one you could give any LLM any context you wanted, that's the whole point after all.

The actual next stage of LLM development will be giving the user the ability to select/deselect what training data to include otherwise there is a limit of at most a few pages of context you can provide.

Custom GPTs are trying to pretend thats what they are doing but it's not going to work.

Like you can't upload a novel and say, "speak to me as if you are this character" because the LLM can't ignore it's training data entirely and the context you give it gets drowned out quickly.

View on HN

My problem with custom GPTs is that it's still building off of the chatbot fine tuned version of GPT-4 which incorporates a hardcoded system message in between yours and the model as well as reflects a very Goodhart's Law driven alignment.

For example, it's next to worthless for creative writing tasks - but it doesn't need to be.

Here is an example of a response to requesting chat suggestions as absurd and bizarre as possible from the current model:

> If you had to choose between eating a live octopus or a dead rat, which one would you pick and why?

It's stochastic so there's a variety but they are generally pretty dry and often information based (explain gravity to flat earthers, describe Earth culture to aliens, etc).

Here was one of the generations from the pre-release chat model integrated into the closed beta for Bing:

> Have you ever danced with a penguin under the moonlight?

I know which one of these two snapshots I'd want to build off of for any kind of creative GPTs, and it's not the one available to power GPTs.

The industry needs SotA competition in alignment strategies and goals badly if we want this tech successful outside of a narrow scope of STEM applications, and the reliance on GPT-4 synthetic data to train its competition isn't helping.

Agreed. Custom gpts, like plugins, feel like a complete distraction to OpenAI

Sometimes I want browsing. Sometimes I want no browsing. Sometimes I want to talk to a marketer. Sometimes to my personal advisor. Sometimes to a python coder. Sometimes to an ML SME. I can quickly change context with a simple @ and select the right context from a dropdown. It's a super fast way to switch the common contexts I use with a LOT less typing.

Wouldn't it be easier to just include in the prompt (please browse web). This seems to work fine with regular ChatGPT.

You can do all of those things with a simple sentence upfront. You'd have to do quite a bit of work to find a GPT that preloads that sentence for you.

Just tell it to browse or not or be a marketer. I don't see the problem custom GPTs are solving for you.

Several identical comments. I find it faster to type @ and select from dropdown.

> From day one you could give any LLM any context you wanted

Yes, but copying it over yourself is inconvenient.

> From day one you could give any LLM any context you wanted, that's the whole point after all.

Not in the case of the web interface to ChatGPT and nontechies who don't want to run their own model and fuddle with the system prompt.

That's the target market for the GPT Store, but OpenAI is doing an utterly terrible job of marketing it to them.

For the select/deselect training data, I assume this means choose which context to pay attention to?

Each ML model, LLM and otherwise, is a combination of matmul operations & nonlinear activation functions on static weights. My understanding of your "ignoring training data" is to change the vector values of the neural network, which is part of what happens during fine tuning.

Curious why telling an LLM to speak like a character, then using few shot examples to anchor the model in a certain personality/tone doesn't suffice? Is it really the training data (meaning the response strays to random nonsense) or is it that the instructions are not good enough?

I think the minimum value is comparable to a desktop shortcut

Reply on news.ycombinator.com