Posts.

1️⃣ Attention-grabbing Hook (first 3-6 characters)

A strong emoji up front (🇨🇭📈🚀🔥) or bold questions like “Did you know...?”.

The ones most correlated with high reach are 🚀, 🔥, 🇨🇭, 💸 (+32%). Emojis in the body matter a lot less.

Overloading on emojis hurts your credibility.

2️⃣ Niche Keyword

In my case, the magic word “Switzerland” boosts my reach and CTR. The 🇨🇭 flag emoji works too

3️⃣ Curiosity Gap

Phrases like “Did you know…?”, “The secret to…”, “Here are my 5 favorites:” or a numbered promise (“7 tricks”) also increase my impressions.

4️⃣ “High-value” words (specifically nouns)

Words the algorithm loves: salary, wages, income, money, S&P 500 and OpenAI. Apparently people love it when I talk about money and AI.

5️⃣ Odd numbers and lists

Odd numbers (3, 5, 7) do better than even ones; and using lists also increases impressions, I guess because they make the tweet easy to read.

6️⃣ Brands and Tickers

Mentioning famous companies like OpenAI, Stripe, Nvidia, Valve, etc... also seems to improve impressions - even SP500 and potentially other “mainstream” stock tickers

7️⃣ Call to Action

This includes a few things that boost not just impressions, but also “engagement”, including:

→ “High-value” verbs that drive clicks: multiply, maximize, diversify. → Using “🧵👇” or something similar to show that the tweet is a thread → Short links

📌 Example of an ideal tweet according to my AI:

“🇨🇭 Did you know you can multiply your salary in Switzerland? Here are my 7 tried-and-tested tricks. 🧵👇 #Dinero”

I’ve got a couple more I haven’t included in the thread...

Want to know what they are? Like and share! 🔥

2/ It all revolves around an algorithm that measures whether a note is “helpful” or not.

First, users rate notes as “helpful,” “somewhat helpful,” or “not helpful.” Then the algorithm uses these votes to train a model that evaluates both how helpful the notes are and the “quality” (or trustworthiness) of the voters. 🧠

3/ But votes alone aren’t enough: you need cross-partisan consensus. That is, support from both left- and right-leaning users. If there’s no agreement between both sides, the note isn’t published. 🤝

This consensus acts as a quality indicator: if it convinces everyone, it’s probably reliable information.

4/ Also, your influence depends on your track record.

If your votes tend to align with the consensus, your weight in the system goes up. If you’re always disagreeing with everyone, your impact goes down.

This prevents biased users from distorting the results. 🎯

(Obviously, this isn’t risk-free)

5/ Abuse is penalized: if a note is marked as offensive by cross-partisan consensus, those who rated it as “helpful” lose credibility. 🛑

That way, the system discourages toxic behavior and rewards constructive participation.

6/ Algorithm summary: • Only notes with consensus between left and right get published. • Reliable users have more weight. • Abuse is punished.

It’s simple in concept, but it raises some questions: • Is this balance sustainable? • Isn’t reducing everything to “left” and “right” a bit simplistic? 🤔

7/ In any case, the system is a fascinating experiment. It’s not perfect, but it seems like a good foundation for managing misinformation on large platforms. And realistically, it works pretty well in practice.

What do you think? 💬

8/ If you want to dig deeper, this post from Less Wrong explains it better than I can: lesswrong.com/posts/sx9wTyCp5kgy8xGac/co…