Today, I'm working on building my own AI writing assistant w/ GPT-3 ✨ Here's the plan: - Explore OpenAI + Playground - Connect to GPT-3s API - Ship a web app + Chrome extension If this seems cool and you also wanna build it, check out buildspace: buildspace.so/builds/ai-writ…

Okay, this is too crazy lol GPT-3 is trained on a massive amount of text from the internet -- which means I can talk to literally anyone I want. Here's me having a convo with Cristiano Ronaldo. cc: buildspace

🤯🤯🤯🤯 I'm amazedddddd!!!!!!!!!

rude

Harsh Truth: Most people don't really care about you. The Spotlight Effect says that we overestimate the degree to which other people are noticing or observing our actions. This is liberating—stop worrying about what others think, be yourself, and live according to your values.

Got this NFT from buildspace ✨

what if you could just describe the website that you want and … boom 💣 👀

I've been working with Golang lately and it feels very familiar. Trying to build a notifications system out of it

🌟 introducing Mabbu ☁️, an auto-diagramming and documentation tool Mabbu allows devs to better understand unfamiliar codebases through interactive graphs and supporting explanations. DM me if you’re interested in trying Mabbu out! buildspace nights & weekends Farza 🇵🇰🇺🇸

the formula I used for going from 0 to 100k users in 19 days

Chandrayaan-3 Mission: 'India🇮🇳, I reached my destination and you too!' : Chandrayaan-3 Chandrayaan-3 has successfully soft-landed on the moon 🌖!. Congratulations, India🇮🇳! #Chandrayaan_3 #Ch3

Developed by two 19-year-old students, these gloves translate sign language into sound.

“As engineers, we were going to be in a position to change the world – not just study it.” — Henry Petroski

how to make fewer dumb decisions: 1. when the long term is unclear, just make good short term decisions. 2. quickly weigh the potential upside vs. downside. 3. if your decision is emotional, don’t pretend it’s logical. 4. when in doubt, just do the math. 5. deciding to do more

Introducing Meta Llama 3: the most capable openly available LLM to date. Today we’re releasing 8B & 70B models that deliver on new capabilities such as improved reasoning and set a new state-of-the-art for models of their sizes. Today's release includes the first two Llama 3

✨ I spent 3 months writing the best interactive introduction to queueing I could, and it's live now! I started this on March 1st, and in total have sunk over 70 hours into refining and perfecting it. It starts off showing what happens without queues...

📽️ New 4 hour (lol) video lecture on YouTube: "Let’s reproduce GPT-2 (124M)" youtu.be/l8pRSuU81PU The video ended up so long because it is... comprehensive: we start with empty file and end up with a GPT-2 (124M) model: - first we build the GPT-2 network - then we optimize

me using vim

realest nigga on the entire planet. God bless this man.

No one can compete with you on being you. Most of life is a search for who and what needs you the most.