LogoThread Easy
  • Explorer
  • Composer un thread
LogoThread Easy

Votre partenaire tout-en-un pour les threads Twitter

© 2025 Thread Easy All Rights Reserved.

Explorer

Newest first — browse tweet threads

Keep on to blur preview images; turn off to show them clearly

I know you think you have great research to share. I don't have time or energy or often even the skill to implement or this or that your research. 

If you want your research to get used by me or nous, please do one of the following:

1. Make a dataset and share it publicly
2. Implement the environment into Atropos
3. Make a PR in our torchtitan fork
4. Make an OS repo and share it

and accompany that with good docs or go all the way and make a paper. 

Thank you for your attention to this matter 🙏

I know you think you have great research to share. I don't have time or energy or often even the skill to implement or this or that your research. If you want your research to get used by me or nous, please do one of the following: 1. Make a dataset and share it publicly 2. Implement the environment into Atropos 3. Make a PR in our torchtitan fork 4. Make an OS repo and share it and accompany that with good docs or go all the way and make a paper. Thank you for your attention to this matter 🙏

Cofounder and Head of Post Training @NousResearch, prev @StabilityAI Github: https://t.co/LZwHTUFwPq HuggingFace: https://t.co/sN2FFU8PVE

avatar for Teknium (e/λ)
Teknium (e/λ)
Mon Nov 10 18:31:39
Deep learning is not a collection of black-box tricks, contrary to what many believe. It can be learned as a principled engineering discipline.

This latest edition of Deep Learning with Python is my best attempt so far at teaching it. It focuses on building deep intuition -- the theory and mental models -- alongside all of the practical programming patterns.

You will learn this on a truly modern stack: Keras 3 as a high-productivity, framework-agnostic API, and preferably JAX for SotA performance and scalability (PyTorch and TensorFlow are also fully supported).

Deep learning is not a collection of black-box tricks, contrary to what many believe. It can be learned as a principled engineering discipline. This latest edition of Deep Learning with Python is my best attempt so far at teaching it. It focuses on building deep intuition -- the theory and mental models -- alongside all of the practical programming patterns. You will learn this on a truly modern stack: Keras 3 as a high-productivity, framework-agnostic API, and preferably JAX for SotA performance and scalability (PyTorch and TensorFlow are also fully supported).

We've made the book content fully available online for free: https://t.co/ktH33YbZp3

avatar for François Chollet
François Chollet
Mon Nov 10 18:27:56
Until the trilemma of plasticity, stability, and editability in digital cognition is resolved, AI will remain a class of formidable approximation engines... powerful, yet fundamentally heuristic.

Until the trilemma of plasticity, stability, and editability in digital cognition is resolved, AI will remain a class of formidable approximation engines... powerful, yet fundamentally heuristic.

Exploring science, cognition, AI, robotics, engineering, dynamical complex systems, more importantly life and beyond. Founder at https://t.co/HInAbA9KEW, and https://t.co/vnHrcX97UC.

avatar for Faruk “Frank” Guney
Faruk “Frank” Guney
Mon Nov 10 18:24:39
Writing a (very) in-depth post on why I canceled my family's health insurance and switched to @JoinCrowdHealth 

Anyone have questions? Will be sure to answer them.

Writing a (very) in-depth post on why I canceled my family's health insurance and switched to @JoinCrowdHealth Anyone have questions? Will be sure to answer them.

Author (Husk, Crypto Confidential): https://t.co/L2COrV5QA3 Building: https://t.co/HMcbuBhTP3 Teaching: https://t.co/Dy0FsZHQaz

avatar for Nat Eliason
Nat Eliason
Mon Nov 10 18:22:21
Facebook Reels are weird, but it seems still A LOT of people there, surprisingly to me.

Also the algorithm weirdly showed my reel for 90% of people who don't follow my Laravel Daily page.

So, I guess it's a huge (unexpected) opportunity channel for spreading good content?

Facebook Reels are weird, but it seems still A LOT of people there, surprisingly to me. Also the algorithm weirdly showed my reel for 90% of people who don't follow my Laravel Daily page. So, I guess it's a huge (unexpected) opportunity channel for spreading good content?

~20 yrs in web-dev, now mostly Laravel. My Laravel courses: https://t.co/HRUAJdMRZL My Youtube channel: https://t.co/qPQAkaov2F

avatar for Povilas Korop | Laravel Courses Creator & Youtuber
Povilas Korop | Laravel Courses Creator & Youtuber
Mon Nov 10 18:21:13
RT @SashaGusevPosts: There are many reasons this leads to biased estimates, w/ multiple papers warning against it. And by comparing the pop…

RT @SashaGusevPosts: There are many reasons this leads to biased estimates, w/ multiple papers warning against it. And by comparing the pop…

Choose disfavour where obedience does not bring honour. I do math. And was once asked by R. Morris Sr. : "For whom?" @halvarflake@mastodon.social

avatar for Halvar Flake
Halvar Flake
Mon Nov 10 18:20:27
  • Previous
  • 1
  • More pages
  • 235
  • 236
  • 237
  • More pages
  • 2111
  • Next