antirez 167 days ago. 56191 views.
My usual process for writing blog posts is more or less in two steps:

1. Think about what I want to say for weeks or months. No, I don’t spend weeks focusing on a blog post, the process is exactly reversed: I write blog posts about things that are so important to me to be in my mind for weeks.

2. Then, once enough ideas collapsed together in a decent form, I write the blog post in 30 minutes, often without caring much about the form, and I hit “publish”. This process usually works writing the titles of the sections as I initially just got the big picture of what I want to say, and then filling the empty paragraphs with text.

Why I take step 2 so lightly? Because I got other stuff to do, and if blogging would take more than 30/60 minutes I would rather not blog at all, or blog less, or suffer doing it: all things I want to avoid at all costs. Blogging is too important to let it go. It’s better, for me, to give up on the form.

At the same time, this is why many of my blog posts, regardless of the content that may be more or less informative, more or less useful, are generally badly written. I hope that the fact I can write well enough in my mother language in some way it is still visibile in my English posts, but I have the feeling that the extremely limited vocabulary I possess, the grammar errors, the sentence construction that oftentimes I just take from Italian and turn into English, all those limits irremediably damage the reading experience.

This is why, for the first time, to write my blog post about LLMs and programming I tried a different approach: I wrote the post in Italian and I translated it to English using GPT-4. The result is a much better blog post than usually, I believe, and the total time to write it was comparable to writing it in English, because writing in Italian in a bit faster, and this compensated the time needed to cut & paste the sections in GPT-4, wait for the output, check that it matched the Italian meaning, and doing a few corrections and rewriting when needed.

It shocks me that I can hear my voice when reading the translation. It does not sound written by somebody else. And, interestingly, the tools to spot GPT generated texts tell me that the post was written “100% by human”. At the same time the process may look a bit synthetic: even worse I may lose confidence writing English if I continue along this path, so I’m still not sure how this blog will be written in the future. One thing is sure: the post you are reading is not just written by myself, but as the tradition in this blog demands, not even re-read or corrected if not for a quick second pass. This way you can see what my written English really is, and if you are curious, compare it with the post about LLMs. The difference is not less than huge.

Another point of view on the matter could be that my true voice is the one of the translated blog post, so writing in English is the real bluff here. Because the translated post is more representative of my lexical ability in my mother tongue, and not of the reduced one I can feature when writing in English. Maybe it captures more shades of what I really want to say. But then one could go deeper in arguments about what style really is. Is it more about sentence construction, and the way you put down your ideas, or is it a lot more about the vocabulary used, the exact words and adjectives selected to provide a given image and meaning? Probably both, and the two things are quite an inseparable whole.

Anyway the simple fact that now, in 2024, I finally have this choice, fulls me of hope and fear. Hope for the possibilities the humanity will have, with machines that can talk. And fear about the potential AI has to make everybody lazy, no longer willing to do things as hard as learning a new language.
🚀 Dear reader, the first six chapters of my AI sci-fi novel, WOHPE, are now available as a free eBook. Click here to get it.
blog comments powered by Disqus