Gabriel Maggiotti

Director, Machine Learning Engineer @ASAPP.
AI practitioner, math lover, programmer, tech & security enthusiast. 
ML, Deep Learning, python, Node & others

[Gabriel Maggiotti @gmaggiotti]

I'm always taking steps in the right direction thanks to my new hat 🤣🤓

[Gabriel Maggiotti @gmaggiotti]

ARC-AGI-2 rising from under 5% to 50%+ in months shows rapid progress. Poetiq points to gains from frontier models and smart orchestration without massive compute.
https://t.co/gOsJhpv3Pu

[Gabriel Maggiotti @gmaggiotti]

@MatiasNisenson 20% always

[Gabriel Maggiotti @gmaggiotti]

Impressed!

[Gabriel Maggiotti @gmaggiotti]

Extremely excited about our latest innovation, a state-of-the-art Generative Agent. We are ready to herald the dawn of a new era in machine intelligence and automation. Join us!
https://t.co/hLxTsZf49e

[SpaceX @SpaceX]

Liftoff of Starship!

[Gabriel Maggiotti @gmaggiotti]

@MatiasNisenson Yes

[Gabriel Maggiotti @gmaggiotti]

Excited to see our paper at NeurIPS! 💪

[Varun Gangal @VarunGangal]

Pretraining LLMs? Scouting 🚄 approximations for nn.linear()?

Coming @ #NeurIPS2023 #WANT WS, @sarin1991 & I explore DYAD - a 2part blocksparse ✖️iable split of weight matrix W.

Pitch https://t.co/mowfkWftP4
Draft https://t.co/BrAhPPGan3
Code https://t.co/Kma2z32Bp2

[Gabriel Maggiotti @gmaggiotti]

monkeytype is incredibly addictive

[Gabriel Maggiotti @gmaggiotti]

@elonmusk Player should have video progress time

[Gabriel Maggiotti @gmaggiotti]

💻🤣 When the terminal becomes a comedy club!

[Gabriel Maggiotti @gmaggiotti]

Life is short, but the happiness that comes from a perfect slice of pizza lasts forever. 🍕❤️ #PizzaLove #Italy

[Gabriel Maggiotti @gmaggiotti]

@julien_c SLLM or XSLLM if is even more smaller

[Gabriel Maggiotti @gmaggiotti]

https://t.co/4GiAp2MnNH

[Gabriel Maggiotti @gmaggiotti]

As the year comes to a close, I can't help but reflect on all the amazing advancements in the world of tech and AI. From large language models to the release of cutting-edge technologies, it's been an exciting year for us. Here's to an even nerdier & exciting year in 2023. #AI

[Lucas Beyer (bl16) @giffmana]

How good of a BERT can one get in ONE DAY on ONE GPU?

With all the recent studies about scaling compute up, this paper takes a refreshing turn and does a deep dive into scaling down compute.

It's well written, stock full of insights. Here is my summary and my opinions.

🧶 1/N

[Gabriel Maggiotti @gmaggiotti]

I just got a chance to work with PaLM and I'm amazed by its capabilities!

[Mark Tenenholtz @marktenenholtz]

Someone implemented a framework to allow you to train PaLM (Google’s 540B parameter LM) using the same reinforcement learning strategy as ChatGPT!

Open source strikes again.

To start, here’s the part where you initially pre-train the model:

[Gabriel Maggiotti @gmaggiotti]

@elonmusk Epic game. Thanks Argentina!!! 💪💪💪

[Gabriel Maggiotti @gmaggiotti]

We are growing our ML Engineering team!!!  If you'd like to work on cutting edge machine learning and natural language processing (NLP) challenges and help us to turn our research into meaningful AI-Native products,  please DM me.…https://t.co/wda4KNsesz https://t.co/lgZSPUOyvK