[0] https://stackoverflow.com/questions/55201372/event-stream-da... [1] https://github.com/EventSource/eventsource/issues/94

Now if the Chrome store stops taking 3-4 days to approve an update, that'd be great!

[1] https://sublimegpt.com

Having GPT fill in (or 'out', if you prefer) the myriad of web-forms I'm currently wrestling with as a job-seeker would be amazing. There's only so many times each day I can copy and paste from my CV (résumé) without turning to drink.

Then you download/subscribe/connect your LLM interface, to your tools. I guess that’s kind of like Slack.

On the first part: I've been trying to build a tool that parses webpages using ChatGPT, but I'm struggling to figure out the best way to pass the website content over. Some options I have tried:

* Raw HTML - expensive, and in a lot of cases doesn't fit in prompt input

* OCR - works better than I would have expected, but can struggle with certain fonts, and a lot of the webpage structure is lost

Maybe stripping the styling and Javascript from webpages would work? Did you do the OCR as part of the complete model or did you make it a separate step? Machine learning is usually much better in one step.

For more context: I have this setup as an api that I feed url + typescript definitions to, and have chatgpt output information from the website in the specified typescript definition.

For example, I can use {product_price: float, product_name: str} + a url as the input, and fairly accurately get product price info across ALL product websites. It's kind of amazing that it's able to do this much just based upon the typescript variable names + raw OCR output.

Wait till they make the image input available via the API, I guess

https://github.com/NotBrianZach/bza (my concept, wip, read along repl as opposed to io focused cli tool)

You could create a graph of the intersections/references of meaning across different books. Those could represent an external memory for the agent/LLM, that it can retrieve/navigate via prompts.

he says it tends to lose character cohesion as conversation goes on

and of course obviously could be useful if a character shows up in a scene it just looks up their wiki entry essentially

sounds complicated lol

i just wanna read math book with it

i could imagine it would be fun to create a wiki with friends and then like randomly roll characters into your session from your shared universe or something

a lot of possibilities

[1] https://chrome.google.com/webstore/detail/autotype-free-text...

I'm building a chrome extension called SublimeGPT[1] to do exactly that. Right now, you can log in to your existing ChatGPT account, go to any page, and open a chat overlay. Next version will have the context options.

[1] https://sublimegpt.com

    function __summarize(api_key) {
        var selection = window.getSelection().toString();
        if (selection.length == 0) return;
    
        var xhr = new XMLHttpRequest();
        xhr.open("POST", "https://api.openai.com/v1/chat/completions");
        xhr.setRequestHeader('Content-Type', 'application/json');
        xhr.setRequestHeader('Authorization', 'Bearer ' + api_key);
        window.scrollTo({top: 0})
        document.body.innerHTML = 'asking...'
        document.body.style.backgroundColor = "white";
        document.body.style.color = "black";
        document.body.style.fontFamily = 'monospace'
        document.body.style.fontSize = "16px"
        document.body.style.margin = "auto"
        document.body.style.padding = "1rem"
        document.body.style.maxWidth = "60rem"
        xhr.onreadystatechange = function() {
            if (xhr.readyState == 4) {
                if (xhr.status == 200) {
                    var response = JSON.parse(xhr.responseText);
                    var summary = response.choices[0].message.content;
                    document.body.innerHTML = summary
                } else {
                    try {
                        var e = JSON.parse(xhr.responseText);
                        document.body.innerHTML = e.error.message
                    } catch(e) {
                        document.body.innerHTML = 'error asking.. check the console'
                        console.log(xhr)
                    }
                }
            }
        }
    
        var data = JSON.stringify({
            "model": "gpt-3.5-turbo",
            "messages": [
                {"role": "system", "content": "Summarize the following text as if you are Richard Feynman"},
                {"role": "user", "content": selection}
            ]
        });
        xhr.send(data);
    }

though i just copy and paste the bookmarklet and change the prompt

I started using Brave.

I'm still collecting all the good ideas to make this highly useful as I don't want to make it just another frontend for ChatGPT. Next version will also let you bring your own API key if you don't want to login to ChatGPT website.