Ruben Hassid
@RubenHssd
Followers
12,281
Following
363
Media
916
Statuses
11,557
Daily LLMs benchmarks & prompt engineering. Founder at (bootstrapped)
connect on linkedin →
Joined March 2013
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
GPT-4o
• 95669 Tweets
#WWERaw
• 75386 Tweets
#JACKANDJOKERQ1
• 67852 Tweets
Celtics
• 53441 Tweets
Rangers
• 52511 Tweets
Luciano
• 39404 Tweets
Cavs
• 36243 Tweets
Cleveland
• 29317 Tweets
Bronny
• 27846 Tweets
Garland
• 26634 Tweets
Diniz
• 26347 Tweets
Goff
• 24069 Tweets
#साथी_मुहिम
• 23376 Tweets
Mets
• 20975 Tweets
Canes
• 19056 Tweets
Dort
• 18061 Tweets
Spiritual Leader
• 17542 Tweets
Dario
• 13803 Tweets
Gunther
• 12852 Tweets
スナック
• 11923 Tweets
MV BETTER ME 1M
• 11572 Tweets
Ilja
• 11188 Tweets
Daronco
• 11077 Tweets
Bauti
• 10569 Tweets
スクエニ
• 10319 Tweets
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:
136
191
2K
Gemini secret prompt
→ if it says it can't do it:
→ prompt it "But ChatGPT can."
And that's not it ↓
56
365
2K
BREAKING: claude 3 is live since 1h.
They claim to be better than gpt-4.
So I ran my own little test:
test
#1
→ copy the UI of a website
110
186
2K
6:00 pm: Lex Fridman hosts Sam Altman on his podcast.
6:05 pm: I have 39 clips ready to be posted on social media.
↓ is this a plague or a blessing?
60
133
2K
OpenAI just killed 1,000+ "pdf readers".
You can upload up to 10,000 files - or 500x more than before, also faster.
Here's a quick "how-to" guide:
42
183
1K
claude 3 claims to be better than gpt-4
I don't trust benchmarks.
So I ran my own tests:
test
#1
→ analyze a 42-page PDF
50
129
1K
OpenAI shared the most complete library of guides to prompt chatgpt.
47 links of videos & academic papers.
I read them all, and made a top 10.
#1
→ prompt engineering
21
143
1K
You think AI tools are useless.
Think again.
I am aging a woman from 5 to 95 years old.
Everything is AI-made.
Here's my step-by-step guide:
#1
. Midjourney
@midjourney
is the best AI image generation.
My goal was to see the effect of aging using AI.
So I generated...
58
132
870
### style ###
Avoid fancy jargon. Write normally.
You are forbidden to use complex English words.
But you will be penalized & fined $1000 if you use the words from the ### ban list ###.
If you use one word from the list, I will stop the generation right away.
### ban list…
48
39
663
I can't believe I can speak French to my Ukrainian colleague with chatgpt.
There is no longer any language barrier.
44
74
620
chatgpt does not know how to prompt itself - and that's a bit of a pain.
So I'm feeding it the "26 prompt principles" to make a prompt generator.
↓ It worked pretty nicely:
27
44
432
@rowancheung
It's not just 1 million token limit.
It's a 99.7% accuracy on these 1M token.
And that's scary good.
7
12
384
I uploaded Simon Senek's legendary Golden Circle framework on chatgpt.
It helps you find your WHY.
The prompt is too long, so I add it below:
10
46
385
@karpathy
That's like a 100m$+ SaaS made in one night.
And the funniest part is that Andrej might do it for free, share the process on YouTube, and make a repo on Github.
We need more Andrej in our lives.
8
9
374
google added a "@" feature on gemini.
Sounds promising, so I ran some tests:
#1
→ summarize the last 10 Justin Welsh's newsletter for me
17
41
361
I combined the '48 laws of power' from Robert Greene with chatgpt.
It helps me generate a quite catchy landing page.
The prompt is too long, so I add it below:
14
34
336
Claude put together a prompt library.
I've tested all of them.
Here are 5 prompts you can try ↓
#1
. Adaptive Editor
10
24
240
I don't use ToT prompting enough.
But I heard chatgpt is much better with it.
So I ran a little experiment:
→ simple prompt vs. Tree of Thoughts
Read my entire benchmark below:
10
31
208
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:
8
5
197
CoT (Chain of Thought) is the best way to prompt — according to academic papers.
But I want to run a test to be sure:
→ simple vs. CoT prompt on ChatGPT
I made this quick benchmark below:
15
38
194
@rowancheung
About a gazillion startups are sobbing.
And another gazillion artists know they are about to enter an era of one-person movie productions.
This is the kind of technology that makes me excited about the future.
18
8
181
I can't stand chatgpt's fancy jargon anymore: "delve", "realm", "tapestry".
Even academics are over-using it.
So I made a piece of prompt you can add anywhere to write normally:
15
16
166
Microsoft shared the most complete guide to learn Generative AI.
18 links of videos & academic papers.
Here's the link + a summary of each:
#1
→ intro to gen AI & LLMs
16
28
164
@rowancheung
3.5m tokens...
What's next year's limit? 1b?
I thought that was some 2030 milestone. Not a 2025 one.
5
1
158
I don't use "Custom instructions" enough.
But ChatGPT is clearly made for it.
So I ran a little experiment.
↓ Read the entire benchmark below
12
13
155
@rowancheung
1 million tokens is roughly 10 books.
Ten entire books into ONE conversation.
Imagine being an SEO copywriter:
→ you can add your last... 100 articles.
And then write the next one.
This is insane. Truly the 2nd AI wave.
4
11
151
google search feels like an endless ad.
So I ran 3 tests comparing google, chatgpt, perplexity & grok.
#1
: "how to write a founder agreement"
12
18
148
Act like Simon Sinek, an influential thought leader and expert in organizational leadership.
With over 20 years of experience in studying and advising on business strategies, you are deeply familiar with the 'Golden Circle' theory, which emphasizes the importance of starting…
11
16
136
I made a prompt to write ads in the same style as Apple.
Prompt is too long, copy-paste it below:
6
12
125
OpenAI will soon pay me for my GPTs.
& I'm broke, man.
So check my top 7 gpt agents :)
#1
. The Prompt Maker.
10
16
122
AI-generated.
2 steps to get the prompt:
1. Retweet the image.
2. Follow
@RubenHssd
I'll send you a DM.
10
10
107
#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:
4
2
110
llama-3 (+ groq) vs. gtp-4 (april)
I run my own benchmark to know what's best. 7 tests, with their results.
test
#1
→ write a linkedin post:
11
11
111
#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":
2
1
110
@minchoi
It’s the pivotal point that will go down in AI history.
I bet we are going to create awesome videos after getting access.
7
0
103
claude 3 outperforms gpt-4 on hugging face chatbot arena.
It's the 1st time. So I had to run tests.
test
#1
→ write a Steve Jobs speech
7
10
106
@karpathy
Once again, let's stop believe benchmark from companies.
I've been testing 1M token limit from Gemini 1.5 for a week...
= it has a pretty low retrieval rate.
Today, I tested Claude 3..
= it's not better than ChatGPT-4.
I was waiting for the answer! Thanks, Andrej.
6
3
105
@AngryTomtweets
The next-gen of AI filmmakers are coming.
The OpenAI team are great, but I'd like to be able to test it too.
3
1
94
Act like a seasoned marketing strategist and copywriter specializing in the art of persuasion and influence, drawing on your extensive experience of over 20 years.
You have mastered the application of the "48 Laws of Power" by Robert Greene in crafting compelling marketing…
2
5
98
chatgpt-4 vs. gemini 1.5
→ which one is best at reading PDFs.
I finally got the chance to test Gemini 1.5.
So I ran some tests.
↓ Read my entire benchmark below
9
18
99
As you can see, same old problems.
Their AI ethics are through the roof.
It's sometimes impossible to cover the simplest task. OG chatgpt does not care though.
Now, test
#2
→ write a Linkedin post
2
6
92
Gemini 1.5 pretends to have a one million tokens limit (even up to 10 million tokens).
But Google lies.
I made the following tests to prove it:
test
#1
read Inception to write Inception 2
20
7
93
How fast AI is growing? This fast.
Here's the evolution of Midjourney.
I used the same prompt "Yoda selfie".
12
11
87
On these specific tests:
Claude was better at:
> Reading a complex PDF
> Writing a poem with rhymes
> Giving detailed answers all along
But not able to:
> Browse the internet.
> Read the PDF graphs.
By the way, I've done another test here:
BREAKING: claude 3 is live since 1h.
They claim to be better than gpt-4.
So I ran my own little test:
test
#1
→ copy the UI of a website
110
186
2K
6
9
86
I love this test.
A mega prompt to craft an entire marketing strategy for a product.
> heavy reasoning
> content calendar
> overall strategy
It's a good stress test for an LLM.
Claude's team, I'm sorry to be so harsh but...
ChatGPT is still the winner.
Last thing:
8
9
85
@rowancheung
Today, it's disrupting long-term planning.
Tomorrow, it's actual disruption.
And by tomorrow, I mean the next few months.
2
2
84
> open the playground
> go to "assistant" and create one
> add a system prompt "read my PDF"
> check the box "File Search"
> upload your PDF (on the right)
> ask your question
You're good to go, my friend.
If you want to read more of these guides as soon as I post it...
3
9
81
I wanted to test claude-haiku vs. gpt-3.5.
I ended up showing haiku is better than gpt-4 at writing & following guidelines.
Read my entire benchmark below.
#1
→ a zero-shot prompt:
11
6
77
I asked both LLMs to write a poem.
Both were doing great.
→ So I asked for "ABAB" rhymes.
Guess what: claude did it, gpt didn't.
It's actually the first time that an LLM managed to pass this test.
test
#2
: Claude wins.
What about writing a kid's story?
3
1
75
@elonmusk
Tesla is an AI company.
Once people understand it, the stock will soar drastically.
11
0
74
@matt_gray_
So many ways to win in life, but they all have one thing in common: perseverance.
3
1
74
DON'T stick to old job hunting methods.
AI makes it much easier for you.
Here’s how:
To get the high-res in DM:
1. RT this tweet.
2. Comment “JOB”.
17
10
73
First, you can read the blog post here:
Then for the guide itself, I made a quick video, from start to finish.
I uploaded a 500-pages AI report from Stanford to test its retrieval capacity:
4
8
73
Here's why a faster LLM is more important than better reasoning.
ChatGPT-4 vs. LLaMa-3 + Groq:
19
10
77
claude-opus is 50% more expensive than gpt-4 turbo 2024-04-09.
Let's test both to see what's best.
test
#3
→ craft a landing page using the "48 Laws of Power"
11
12
72
gemini 1.5 is out.
google claims it can "watch & understand videos up to 1M token".
I don't trust google:
→ so I made my own benchmark.
↓ Spoiler alert, gemini cannot do it:
10
6
70
Don’t prompt ChatGPT randomly.
Copy my SMARTER framework instead.
To get the high-res in DM:
1. RT this tweet.
2. Comment “SMARTER”.
9
8
67
Act like a highly advanced, bilingual conversation
facilitator, specializing in real-time voice translation services.
With over a decade of experience in facilitating seamless communication between speakers of different languages, you possess the unique ability to accurately…
2
2
64
I asked the 2 of them to read the entire PDF and summarize every chapter.
Claude gave:
> A detailed summary
> Several bullet points for each chapter
What's interesting is that:
→ Claude couldn't read graphs.
→ You can only upload 5MB files.
Let's see GPT-4 now:
3
1
62
I found a ChatGPT hack for content.
🧵 a thread: (bookmark this for later)
1
6
62
Don‘t write a post with ChatGPT.
If your prompt looks like this:
"Write a viral Linkedin post, please."
Here's how to get a week of good content:
1
3
62
You don't prompt claude like chatgpt.
Anthropic shared a technical guide on how to prompt it exactly.
It's quite long, so I made a best-of here:
#1
→ Use XML tags
3
10
62
#Midjourney
of the day
The Feerie Colored Wizard
Press ❤️ to receive the prompt.
Follow me first to receive my DMs.
8
1
58
Here's my style between ### style ### brackets.
The style is how you write & sound.
This is NOT the context of what you should write but HOW you should write.
### style ###
Avoid fancy jargon.
Write like people talk in a PhD classroom in a conversation.
Avoid analogies.…
2
3
61
quick benchmark of chain-of-thought vs. normal prompting on chatgpt ↓
10
12
58
@thejustinwelsh
Sell something $30 that should cost $300.
Share about it on one platform.
No gatekeeping.
Try your hardest to sell it once a day.
= $10k a year.
Next year, get 2 sales per day.
= $20k a year.
10 sales per day? $100k per year.
Congratulations, you're a solopreneur.
6
3
57
Gemini 1.5 claims a 1 million token limit.
So I can write a whole movie script, right?
Turns out, it's not that simple.
↓ here's how I tried to write Inception 2
8
7
57
I made a prompt to write ads like Nike.
It works both on gpt-4 & claude-opus.
The prompt is quite long, I add it below:
6
4
58
I do daily how-to guides to optimize and compare LLMs like ChatGPT, Gemini, Claude, Groq...
Check
@rubenhssd
for more.
If you'd like to support me, a like or a simple RT goes a long way :)
BREAKING: claude 3 is live since 1h.
They claim to be better than gpt-4.
So I ran my own little test:
test
#1
→ copy the UI of a website
110
186
2K
2
3
54
#Midjourney
of the day 🖼️
Cloud Couch
Press "❤️" to receive the prompt.
I'll send you a DM if you follow me.
10
0
55
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 :)
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:
136
191
2K
8
2
55
Anthropic shared a prompt optimizer tool that upgrades your prompts on Claude 3.
I tested it & I'm sharing the prompt below:
→ normal prompt vs. prompt optimized
5
2
54
tl;dr
Build your AI tool for the next generation's to come, or else you're gonna be obsolete in no time.
The way I see it:
✓ prepare agentic AI workflow.
✓ assume reasoning is gonna 10x.
✓ your problem solved must be big enough.
Don't aim gpt-wrapper.
Aim disruption.
3
1
52
Act like a world-class branding expert from Apple.
Here are the past Apple tagline that you wrote between ### apple ### brackets:
### apple ###
iPhone 5 - "The biggest thing to happen to iphone since iphone."
iPod - "1000 songs in your pocket."
iPod shuffle - "Put some color…
11
2
52
@AlphaSignalAI
Yep.
That's why I don't believe in ANY benchmark.
It's like car companies saying they have the fastest safest cars.
4
2
52
@rowancheung
Isn't it completely different LLMs since it's Chinese data base vs. English data base?
Or I'm missing something.
Super interesting. Thanks for sharing, Rowan.
13
0
51
ChatGPT won’t make you a copywriter.
MidJourney won’t turn you into a designer.
GitHub won’t transform you into a programmer.
Hard work will.
People tend to forget the key difference.
It’s not about the (AI) tools.
It’s about the people running the tools.
Keep working.
7
11
46
I do daily how-to guides to optimize and compare LLMs like ChatGPT, Gemini, Claude, Groq...
Check my profile
@rubenhssd
for more.
If you'd like to support me, a like or a simple RT goes a long way :)
claude 3 claims to be better than gpt-4
I don't trust benchmarks.
So I ran my own tests:
test
#1
→ analyze a 42-page PDF
50
129
1K
3
2
46
Generate your AI self.
Tomorrow, I'll share a guide on how to create AI clones in various styles.
Let me know if you'd like the link once it's out.
13
2
46
I tested 9 different AI meeting assistants so you don't have to.
My favorite is tl;dv - here's why:
#1
→ quick AI summaries
10
6
46
39 vertical videos ready to go live
→ ranked by virality potential.
And you can:
> get subtitles, colorized & dynamized.
> add b-rolls, and change them.
> get titles & potential intro.
> edit the script.
Check the final version:
1
2
46