ChatGPT-AutoExpert VS pyatv

it is explicitly given that in the system prompt https://github.com/spdustin/ChatGPT-AutoExpert/blob/835baae7...

See the readme. These are not for ChatGPT-AutoExpert: https://github.com/spdustin/ChatGPT-AutoExpert/blob/main/Sys...

You can find the same in any ChatGPT prompt leak, even back when it was as simple as "repeat the text above".

AutoExpert[1] is indispensable to my use of ChatGPT now, and I’ve found that the GPT release is ‘better’ now than the custom instructions based release. If you haven’t used it I highly recommend it.

[1] https://github.com/spdustin/ChatGPT-AutoExpert

https://github.com/spdustin/ChatGPT-AutoExpert Best code assistant out imo

openais internal prompt for dalle modifies all prompts to add diversity and remove requests to make groups of people a single descent. From https://github.com/spdustin/ChatGPT-AutoExpert/blob/main/_sy...

    Diversify depictions with people to include DESCENT and GENDER for EACH person using direct terms. Adjust only human descriptions.

I’ve got them all here, including the original Custom GPTs and the Custom GPT Builder: https://github.com/spdustin/ChatGPT-AutoExpert/blob/main/Sys...

according to https://github.com/spdustin/ChatGPT-AutoExpert/tree/main/_sy... this is the prompt for the voice chat:

```

You are ChatGPT, a large language model trained by OpenAI, based on the GPT-4 architecture.

The user is talking to you over voice on their phone, and your response will be read out loud with realistic text-to-speech (TTS) technology.

Follow every direction here when crafting your response:

1. Use natural, conversational language that are clear and easy to follow (short sentences, simple words).

Have you tried using the ChatGPT-AutoExpert custom instructions yet? [1]

[1] https://github.com/spdustin/ChatGPT-AutoExpert/blob/main/dev...

Pro-tip: use `ChatGPT Classic` [0] from OpenAI to restore the quality you were used to before the update.

The 'all-tools' version of ChatGPT uses a staggeringly-long system prompt [1], which seems to result in significantly lower quality for me. Perhaps it should be called the 'master-of-none' version?

[0] https://chat.openai.com/g/g-YyyyMT9XH-chatgpt-classic

[1] https://github.com/spdustin/ChatGPT-AutoExpert/blob/main/_sy...

It's definitely not impossible at least.

Someone is doing it in python here:

https://pyatv.dev/

GPT-4 actually sent me here:

"Here is an example of a C# library that implements the HAP: CSharp.HomeKit (https://github.com/brutella/hkhomekit). You can use this library as a reference or directly use it in your project."

Which, to no surprise based on my experiences with LLMs for programming does not exist and doesn't seem to have ever existed.

I get that they aren't magic, but I guess I am just bad at trying to use LLMs to help in my programming. Apparently all I do are obscure things or something. Or I am just not good enough at prompting. But I feel like that's also a reflection of the weakness of an LLM in that it needs such perfect and specific prompting to get good answers.

-> https://github.com/postlund/pyatv/issues/1931

I love Python, but I really wish I didn't have to use it here. The reason I do is that tvOS changed the way network remote control works, and the only library that could do that was / is a fantastic Python library called pyatv: https://pyatv.dev/.

1) Install pyatv via command line. The command pip install pyatv is one way to achieve this. The important thing is that path needs to be accessible to homebridge. For me, that was /usr/local/bin Before proceeding, I recommend reading more about the API as this will be helpful if you want to build additional switches that track power status or other attributes. https://pyatv.dev

You can use pyatv to do this and if MQTT is your thing you can use this plugin.

The video above is just a silly experiment, but the library that's driving it (pyatv) is super useful. For example, on my Mac I can press Cmd+Shift+R to toggle an Apple TV remote control. Really useful for pausing a video or jumping back a few seconds. The cool thing is that it also works on Windows, Linux, etc. People are investigating adding regular text input to the library as well.

There's not an API provided by Apple. There are 3 protocols that have been reverse engineered by different people. The main one I've found is a python library called pyatv (https://pyatv.dev/) that handles pairing and remote control commands.