Ruben Hassid Profile picture
Mar 26, 2024 6 tweets 3 min read Read on X
chatgpt loves stupid words & I am sick of seeing them all over the web.

I wrote a piece of prompt to avoid this "dive", "realm", "unveiling" madness.

↓ And it worked pretty nicely: Image
#1 → I asked chatgpt to write an article about quantum computing.

It's a difficult subject.

But chatgpt always uses the same jargon → unveiling, dive, realm, etc.

As soon as I see them, I'm like:
= written by (a bad) chatgpt (prompt).

→ So I made a list of "ban words":
So I edited the first prompt by adding:
> my style
> gaslighting chatgpt
> a long list of banned words

And I finally have it:
→ a piece of prompt to add anywhere.

Once added, chatgpt no longer uses fancy jargon and bs wordings.

I run another test to safeproof it:
#2 → I asked chatgpt to write about dollar cost averaging (DCA).

I added my anti-bs prompt at the end.

And I got:
> a clear article about DCA
> no banned words from my list
> no fancy jargon or weird English

Here's the full prompt below:
### style ###

Avoid fancy jargon. Write normally.

You are forbidden to use complex English words.

But you will be penalized & fined $1000 if you use the words from the ### ban list ###.

If you use one word from the list, I will stop the generation right away.

### ban list ###
Hurdles
Bustling
Harnessing
Unveiling the power
Realm
Depicted
Demistify
Insurmountable
New Era
Poised
Unravel
Entanglement
Unprecedented
Eerie connection
unliving
Beacon
Unleash
Delve
Enrich
Multifaced
Elevate
Discover
Supercharge
Unlock
Unleash
Tailored
Elegant
Delve
Dive
Ever-evolving
pride
Realm
Meticulously
Grappling
Weighing
Picture
Architect
Adventure
Journey
Embark
Navigate
Navigation
dazzle
### ban list ###
### style ###

PS: if you eventually find another bs word, you can add it to your style :)

PPS: you can also add a one-shot example of your writing style.

Last thing before you scroll away:Image
I run daily tests on LLMs like chatgpt, gemini & claude to master them.

Check @rubenhssd for more.

If you'd like to support me, a like or a simple RT helps me for free :)

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Ruben Hassid

Ruben Hassid Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @RubenHssd

May 19
Most ChatGPT answers are "yes-man."

After I began using the RPT prompt technique, ChatGPT cut its wrong answers by 40% and gave me much better results.

Here's what the RPT technique is and how to use it:

(my exact prompt + example) Image
To prompt better, first understand why AI is so agreeable.

AI gets trained by human feedback (Reinforcement Learning from Human Feedback)

When we give thumbs up to answers that sound good, the AI learns to say what makes us happy.

It's pleasing us, not checking facts. Image
The fix was discovered in January 2025 by Tsinghua University researchers.

They developed "Reasoning-through-Perspective-Transition" (RPT) prompting and tested it on 12 different types of questions.

It worked much better than regular methods by making the AI argue with itself. Image
Read 13 tweets
May 15
AI is eating up consulting.

I used 3 prompts on ChatGPT to mimic a $600/hour consultant, achieving in 4 hours what takes weeks for teams.

Here's how to make ChatGPT your pocket-sized McKinsey consultant:

(my exact prompt + examples) Image
There are 3 main tasks that a consultant does:

1. Research
2. Making slide decks
3. Reading reports

I'll show you how to automate all 3 in a way that makes one person do the work of an entire team.
Task 1: Research

Go to ChatGPT, use o3 + Deep Research.

Type this prompt:

"As a Big Four consultant, execute a DMAIC-driven Deep Research
workflow in ChatGPT—Define, Measure, Analyze, Improve, and
Control data on [topic]—structuring findings in MECE-compliant
categories into a concise executive summary."
Read 14 tweets
Jan 29
BREAKING: a new Chinese model is out.

And no. This is NOT DeepSeek.

Meet Qwen-2.5, from the giant Alibaba:

1. It can code, write text, search the web.
2. It can generate images, like Dall-E.
3. It can even generate videos.

Here's everything you need to know:
1. Omni-modal mastery:

☑Handles document parsing (tables, charts, handwriting)

☑ Object grounding (JSON coordinates)

☑Long video (hours-long footage with second-level event localization)

☑ Generates structured outputs for invoices, forms & spatial reasoning tasks

2. Scalable architecture

☑ Available in 3B, 7B, and 72B parameter sizes

☑ Proprietary MoE variants (Qwen2.5-Turbo/Plus) for enterprise-scale efficiency. Image
Read 8 tweets
Jan 20
BREAKING: DeepSeek released R1.

And it's already better than ChatGPT o1.

1. It's open-source.
2. API is 96.4% cheaper than chatgpt.
3. I run my tests below. A quick thread:
test #1 → act as an indie hacker to promote my SaaS business.

DeepSeek is so fast. It's insane.

It gave me an entire strategy in 7 actionable steps. So I asked for more:
I asked it to give me new strategies.

It suggested growing profiles with EasyGen and sharing the results.

That's actually what I did with my employees. I'm impressed.

Then, last test:
Read 6 tweets
Dec 30, 2024
DeepSeek is shaking up the AI industry.

1. It's open-source.
2. It's multimodal (images, PDFs...).
3. API is 94.81% cheaper than chatgpt.

I run my own tests below:
#1 → write an SEO-optimized article
#1. Search the web + write an SEO article

> DeepSeek provided 50 sources.
> chatgpt provided roughly 20 sources.

The article is even better than chatgpt.

DeepSeek won. Next test:
#2. DeepThink reasoning

It can reason while reading PDFs. So I uploaded a deck & asked for an article.

chatgpt o1 can only reason while reading images, not PDFs.

DeepSeek results are even faster.

Now, last test:
Read 5 tweets
Nov 14, 2024
I manage my employee's Linkedin.

We went from 0 to 3,836,555 impressions in exactly 178 days of daily posting.

The trick is... I didn't write any posts.

I do this instead: Image
Step 1: Pinterest

1. I go to Pinterest. I pick a viral quote.
2. Copy-paste it on ChatGPT.
3. Ask it to extract the quote.
Step 2: Ideogram

1. Go to Ideogram.
2. Ask for viral images with a quote.

My prompt here:

"a realistic whiteboard where it's written in bold [quote]"

Then, remix, iterate & choose a visual.

Last step:
Read 6 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(