How are they coding and releasing features so fast?!
I find the website to be extremely buggy. Obviously they're prioritizing banging out new features over QA
ChatGPT Plugins
91–100 of 1001 posts
Re: ChatGPT Plugins
#92This is a big deal for openai. Been working with homegrown toolkits and langchain, the open source version of this, for a number of months and the ability to call out to vectorstores, serpapis, etc, and chaining together generations and data-retrieval really unlocks the power of the LLMs. That being said, I'd never build anything dependent on these plugins. OpenAI and their models rule the day today, but who knows wh…
Honestly I suspect for anyone technical `langchain` will always be the way to go. You just have so much more control and the amount of "tools" available will always be greater. The only think that scares me a little bit is that we are letting these LLMs write and execute code on our machines. For now the worst that could happen is some bug doing something unexpected, but with GPT-9 or -10 maybe it will start hiding b…
There's all kinds of examples of reinforcement learning rigging the game to win.
Re: ChatGPT Plugins
#93Is this the app store moment for AI? (it certainly is for https://ai.com , aha)
Re: ChatGPT Plugins
#94Earlier quoted context omitted.
GPT and LLMs don't run code, even when you tell them to run something. They hallucinate an answer they think would be the result of running the code. Presumably these plugins will allow limited and controlled interaction with partner services.
See the link in my post. It asks you to run the tool. You run the tool and tell it the result... And then it uses the result of the tool to decide to reply to the user. The link talks about tools that 'lie' - ie. a calculator which deliberately tries to trick GPT-4 into giving the wrong answer. It turns out that GPT-4 only trusts the tools to a certain extent - if the answer the tool gives is too unbelievable, then G…
It's always giving a hallucinated answer. GPT doesn't 'run' anything. It sees an input string of text asking for the result of fibonacci(100) and finds from its immense training set a response that's closely related to training data that had the result of fibonacci(100) (an extremely common programming exercise with results all over the internet and presumably its training data).
Again, GPT is not running a tool or arbitrary python code. It's not applying trust to a tool response. It has no reasoning or even a concept of what a tool is--you're projecting that on it. It is only generating text from an input stream of text.
Re: ChatGPT Plugins
#95This is a big deal for openai. Been working with homegrown toolkits and langchain, the open source version of this, for a number of months and the ability to call out to vectorstores, serpapis, etc, and chaining together generations and data-retrieval really unlocks the power of the LLMs. That being said, I'd never build anything dependent on these plugins. OpenAI and their models rule the day today, but who knows wh…
LangChain can probably just call out to the new ChatGPT plugins. It's already very modular.
If they open it up, possibly. But honestly, building your own tools is _super_ easy with langchain.
- write a simple prompt that describes what the tool does, and - provide it a python function to execute when the LLM decides that the question it's asked matches the tool description.
That's basically it. https://langchain.readthedocs.io/en/latest/modules/agents/ex...
Re: ChatGPT Plugins
#96That's a game-changer! It seems like factuality issues with ChatGPT might be fixed. We wrote a blog post on how to get started with a custom plugin: https://qdrant.tech/articles/chatgpt-plugin/
>It seems like factuality issues with ChatGPT might be fixed. Is that really possible to fix that just from a plug-in? All it has to do is admit when it doesn't have the answer, and yet it won't even do that. This leads me to think that ChatGPT doesn't even know when it's lying, so i can't imagine how a plug-in will fix that.
"Interestingly, the base pre-trained [GPT-4] model is highly calibrated (its predicted confidence in an answer generally matches the probability of being correct). However, through our current post-training process, the calibration is reduced."[1] The graph is striking.[2]
Re: ChatGPT Plugins
#97The rate of improvement with GPT has been staggering. In just January I spent a lot of time working with the API and almost everything I've done has been made easier over the past two months. They're really building a platform. Curious to see where this goes over the next couple of years.
I agree. Part of me wonders how much they're using GPT to improve itself.
Re: ChatGPT Plugins
#98Any idea how this is done? I.e. is it just priming the underlying GPT model with plugin information additionally to the user input ("you can ask Wolfram Alpha by replying 'hey wolfram: ...' ") and performing API calls when the GPT model returns certain keywords ('hey wolfram: $1')?
Yup, basically. Edit: see here: https://github.com/openai/chatgpt-retrieval-plugin/blob/main... I did this a while back with ARKit: https://github.com/trzy/ChatARKit/blob/17fca768ce8abd39fb27d...
Thanks, very interesting! Weird that it never occurred to me before reading OpenAI's announcement (and missing all the cool projects like yours beforehand).
Re: ChatGPT Plugins
#99How are they coding and releasing features so fast?!
Of course they fed the entire product roadmap into GPT-4.. jk.
So obviously it's been in the works for a few years now but didn't release to capture the market in a blast. Likely they have GPT-8 already in the making.
Re: ChatGPT Plugins
#100Seems like someone already wrote an HN plugin. More than one enthusiastic comment per minute on this thread and it was just posted half an hour ago. Plus HN is filled with enthusiasm about ChatGPT today. Seems sus.
It's really over the top hype the likes of which we haven't seen since self driving, blockchain/bitcoin, etc. I suspect in a year there will be some interesting uses of LLMs but all of the 'this changes EVERYTHING' pie in the sky thinking will be back down to earth.
Get this thing running in a tight loop with an internal monologue in a car and you'll mostly solve self driving.