Thank you for sharing this. FYI, when I run it, it hangs on “Preparing explanation...”. I have an OpenAI account, where I use the gpt-3.5-turbo model on the per-1K-tokens plan. I copied a sentence from your text and your prompt from the source code, and got an explanation quickly, using the same API key. I don’t actually have the ChatGPT Plus subscription, so maybe that’s the problem.
ChatGPT has changed the way I read content, as well. I have a browser extension that downloads an article into a Markdown file. I open the Markdown file in Obsidian, where I have a plugin that interacts with OpenAI. I can summarize sections or ask for explanations of unfamiliar terms.
On the server side, Less Wrong has a lot of really good content. If that content could be used to fine-tune a large language model… it would be like talking to ChatLW instead of ChatGPT.
Things like explanations and poems are better done on the user side, as you have done.
I managed to solve this issue, which appears to be a widespread problem with accessing ChatGPT via the API. The fix is incorporated to the code on Github.
Thank you for sharing this. FYI, when I run it, it hangs on “Preparing explanation...”. I have an OpenAI account, where I use the gpt-3.5-turbo model on the per-1K-tokens plan. I copied a sentence from your text and your prompt from the source code, and got an explanation quickly, using the same API key. I don’t actually have the ChatGPT Plus subscription, so maybe that’s the problem.
ChatGPT has changed the way I read content, as well. I have a browser extension that downloads an article into a Markdown file. I open the Markdown file in Obsidian, where I have a plugin that interacts with OpenAI. I can summarize sections or ask for explanations of unfamiliar terms.
On the server side, Less Wrong has a lot of really good content. If that content could be used to fine-tune a large language model… it would be like talking to ChatLW instead of ChatGPT.
Things like explanations and poems are better done on the user side, as you have done.
Edit:
I managed to solve this issue, which appears to be a widespread problem with accessing ChatGPT via the API. The fix is incorporated to the code on Github.