GPT ☆∴｡ * ･ﾟ*｡★･ @oretapp

Joined August 2021

Tweets

110
Followers

170
Following

5
Likes

363

Shubham Saboo @Saboo_Shubham_

2 years ago

Step-by-step tutorial with Code: theunwindai.com/p/build-an-ai-…

1 4 41 6K 97

View Details

Why does every project feel like it's never delivered on time based on initial estimates? Dave Stewart explains the hidden work within the work in an excellent visual. The entire post can be found at davestewart's blog post "the work is never just the work"

33 552 5K 485K 6K

View Details

Moon Dev @MoonDevOnYT

2 years ago

Finding the NEXT big CRYPTO with Python & CoinGecko API

2 19 168 8K 176

View Details

Guillermo Rauch @rauchg

2 years ago

Rerun.io is one of the most impressive applications of modern browser tech. It's a Rust-based immediate mode UI app compiled to the web via Webassembly targetting WebGPU. The whole app is just a large <canvas>.

35 166 2K 205K 2K

View Details

Kaj Sotala @xuenay

2 years ago

Okay I think I can co-sign the "if you are having emotional problems, try talking about them with Claude" thing now

16 20 859 103K 237

View Details

ℏεsam @Hesamation

2 years ago

Andrej Karpathy on Tensor Cores and TF32 precision

14 134 2K 113K 1K

View Details

Shivam Rawat @thehermitdev

2 years ago

Building a notes app for myself using Just make small progress with 0.0.1. @vercel @excalidraw @appwrite #buildinpublic Upcoming features: - Keyboard shortcuts. - Pinned notes. - Search feature. DEMO: annotate-notes.vercel.app

1 1 0 35 0

View Details

@

2 years ago

One more reason why everyone should learn C

21 50 471 84K 221

View Details

Dr. Nicole LePera @Theholisticpsyc

2 years ago

I created and produced a mediation on getting out of survival mode that drops tomorrow. Enter your email to get it: theholisticpsychologist.com/newsletter/

13 23 352 51K 90

View Details

Bojan Tunguz @tunguz

2 years ago

This looks extremely promising. Physical activity is one of the best mood improving "drugs". But like with all the other treatments, exact dosage and frequency are crucial. Which, unfortunately, has not been looked into systematically until now.

Nicholas Fabiano, MD @NTFabiano

2 years ago

Our paper was just published in Sports Psychiatry. 🧵1/13

117 769 5K 725K 4K

24 21 212 25K 90

View Details

Pedro Domingos @pmddomingos

2 years ago

ASML: big moat TSMC: medium moat Nvidia: small moat OpenAI: no moat

102 133 2K 439K 822

View Details

Ethan Mollick @emollick

2 years ago

Deep genius is not always broad genius. It can be, but there are far fewer polymaths out there than people who think they are polymaths.

6 7 97 8K 8

View Details

Moon Dev @MoonDevOnYT

2 years ago

openai just made traders irrelevant and its only year 2

321 932 9K 1.6M 15K

View Details

Harris Rothaermel @DeveloperHarris

2 years ago

its happening

Harris Rothaermel @DeveloperHarris

2 years ago

the markets haven’t priced in how disruptive global low latency internet access from satellite constellations will be it’ll be the biggest labor arbitrage in the history of the world

14 28 444 631K 162

98 211 2K 781K 829

View Details

Alex Northstar @NorthstarBrain

2 years ago

Check out the full paper here, good stuff: arxiv.org/pdf/2312.16171…

1 2 23 5K 30

View Details

Alex Northstar @NorthstarBrain

2 years ago

9. When formatting your prompt, start with ‘###Instruction###’, followed by either ‘###Example###’ or ‘###Question###’ if relevant. Use one or more line breaks to separate instructions, examples, questions, context, and input data.

1 1 27 7K 16

View Details

Alex Northstar @NorthstarBrain

2 years ago

8. Allow the model to request precise details and requirements from you by asking you questions until it has enough information to provide the needed output (for example, “From now on, I would like you to ask me questions to...”).

2 1 23 7K 5

View Details

Alex Northstar @NorthstarBrain

2 years ago

6 Use the phrase ”Answer a question given in a natural, human-like manner” in your prompts. 7. Use leading words like writing “think step by step”.

2 1 20 7K 6

View Details

Alex Northstar @NorthstarBrain

2 years ago

3. Employ affirmative directives such as ‘do,’ while steering clear of negative language like ‘don’t’. 4. Add “I’m going to tip $x for a better solution!” LOL 5. Incorporate the following phrases: “Your task is” “You MUST” “You will be penalized”.

2 1 27 8K 17

View Details

Alex Northstar @NorthstarBrain

2 years ago

1. No need to be polite with LLM so there is no need to add phrases like “please”, “if you don’t mind”, “thank you”, “I would like to”, etc. Get straight to the point. 2. Break down complex tasks into a sequence of simpler prompts in an interactive conversation.