I Let AI Build My Blog From Telegram Posts

I crap-coded, sorry, vibe-coded – that is what they call it now.
As an experiment to see whether a top Codex-like model can build something complete and working on top of an existing codebase, I decided to give it a task that was not too critical but still interesting: to build my blog.
I want to write, but I do not want to commit to writing regularly, so I needed a workaround. That is how the whole system appeared:
1. On a schedule, all posts from my Telegram channel (this one) are imported automatically.
2. They are passed through GPT-5.1: translate, generate a title, and create tags.
3. The translation is stored in the database.
4. Images (if any) are uploaded to S3.
You can see the result here: https://tobishua.com/blog
My contribution there: a few edits (simply because I cannot stand bad code architecture) and lots and lots of prompts.
More to explore
How Watching Exchange Rates Replaces Reading the News
Another useful side of tracking exchange rates in real time is that I learn about world events without reading the news. I do not have time to read the media ri…
Fullyst 2025 in Numbers: Growth, Usage, and the Weirdest Spam
All right, I’ll still write a bit about the 2025 results, but for now only about Fullyst. Some stats: 1. Subscriber growth for the Fullyst news channel: +716 pe…
Saylify: web app progress, search experiments, and current pain points
Saylify progress update: I have started on the web app and so far it is going quite well. There is summary, translation, summary of the translation and similar …
Turning My Life Upside Down at the End of a Crazy Year
It seems like it is time to write year-end summaries and plans for the next one, but it looks like I am not up for that. As this insane 2025 is wrapping up, I d…