DearDiary 1.0 Help

On using AI to write about writing

One thing is for sure, I'm using GitHub Copilot and it's massively helpful. But it's kind of weird as well as it influence the way I write.

It makes me write thing

write_thing.png

But it also writes things I would have written anyway. Which is even weirder. Am I that predictable ? Or is it just that good ?

predicatable.png

Am I predictable because I'm using it and it's influencing the way I write ? It is, of course, "that good" and I'm not worried about this. I'm more worried about the fact that it's influencing the way I write.

worthy.png

Talk about weird. It's like a feedback loop. Am I enshitifying myself ?

enshitifying.png

No I'm not... I hope so.

  • I don't have to accept every suggestion.

  • I can influence its suggestions by writing what I want. (and it's just completing it)

On influencing the AI

I'm gonna ask github copilot chat.

Ha yes, sometime I forget that it's specialized in code.

Let's ask bard.ai then.

influence_bard.png

(Well, nope, I wasn't asking you copilot, but thanks for the suggestion)

Haaa yes, it's a chatbot meant to answer questions. So it tell me how write better question ...

Bing then ?

Haaa yes, it's a search engine. So it tell me how to search better ...

I'm not sure what I was expecting.

Let follow the advice of the AI and ask Copilot Chat again.

copilot-write-chapter.png

Ask Copilot Chat to write about itself

GitHub Copilot is an AI-powered code completion tool developed by GitHub and OpenAI. It's designed to assist developers by providing suggestions for completing lines or blocks of code. It's built on the GPT-3 model, which is a language prediction model that uses machine learning to produce human-like text.

GitHub Copilot is trained on a diverse range of public code repositories, which means it can generate code in over a dozen languages and can handle a wide variety of coding tasks. It's designed to understand the context of your code and provide relevant suggestions.

However, it's important to remember that GitHub Copilot is a tool, not a replacement for a developer. It doesn't understand code in the same way a human does. It doesn't know what your code does, it doesn't understand your intentions, and it can't make creative or strategic decisions. It simply predicts what line of code is likely to come next, based on the code it was trained on.

While GitHub Copilot can be a powerful tool for speeding up coding tasks and exploring new coding patterns, it's essential to review and understand the suggestions it provides. It's also important to remember that GitHub Copilot doesn't guarantee the correctness of the code it suggests, and it's up to the developer to ensure the code is correct, secure, and efficient.

In conclusion, GitHub Copilot is a powerful tool for developers, but like any tool, it's effectiveness depends on how it's used. It's a partner in the coding process, not a replacement for a skilled developer.

Asking Bing chat to write about writing a diary using AI

Using the "redactor" thingy, setting : Funny, Paragraph, Medium length.

"Dear Diary" indeed.

A few things there. It's not funny and I'm not 12.

And it sucks at haiku.

This clearly isn't going anywhere.

I didn't try Jetbrains AI Assistant. It doesn't work in WriterSide.

Then, perhaps, I shouldn't worry that much about it. As soon as I filter out the suggestions that are not relevant, it's not that bad. It is simply finishing my sentences. It's not writing for me.

Here come Mixtral

I just heard about Mixtral from Mistral AI, it's more than free, it's open source.

So, dear AI, Write a diary on the topic of "Writing about writing with AI"

It ran, albeit very slowly, on my cheap HP Laptop with 16GB of RAM and no GPU. gg !

In order to run it I used LM Studio and the Mixtral Instruct Q2 Model ("Extreme loss of quality"). I am sincerely impressed by the quality of the text generated by this model considering it's the "Extreme loss of quality" version.

I need to try the Q4 model, as well the "Doplhin Mixtral" model which is "unfiltered" (whatever that means).

Last modified: 23 January 2024