Joined July 2019
- Tweets 419
- Following 577
- Followers 764
- Likes 1,072
126 Photos and videos
20 Apr 2023
🤓 Want to keep on top of what's trending on GitHub?
🤯 Look no further...
linkedin.com/newsletters/git…
#datascience #data #tech #ai #machinelearning #generativeai #github
1
3
936
25 Jan 2023
A tremendous explanation of how ChatGPT is trained youtu.be/VPRSBzXzavo
#generativeAI #AI #openAI #gpt3 #machinelearning #llm #transformer #deeplearning
1
6
1,255
5 Jan 2023
Kicking off 2023 with more exciting generative publications! Here's MUSE (text-to-image) from Google
muse-model.github.io/
No diffusion models - just VQ-GAN tokenisers and pure Transformers all the way!
#generativeAI, #AI #machinelearning #deeplearning #DALLE #ChatGPT
5
873
3 Jan 2023
A comparison of the model sizes of important large language models (yellow) and multimodal models (pink).
#GenerativeAI #AI #DeepLearning #LLM #ChatGPT #gpt4 #GPT3 #stablediffusion
1
2
8
1,005
3 Jan 2023
Updated version of the Generative AI timeline, featuring more LLMs 💪
#GenerativeAI #AI #DeepLearning #LLM #ChatGPT #gpt4 #GPT3 #stablediffusion #dalle
2
4
799
1 Jan 2023
Generative AI in 2023 will be crazy good - I can't wait🤗
Need a recap of how we got here?
Check out this timeline of some of the major model milestones achieved so far🚀
🥳 Happy New Year!
#generativeAI #AI #aiart #deeplearning
3
14
70
20,361
23 Nov 2022
Love this - this blend of #generative #AI, #RL and active inference will be a fascinating area of development over the next 2-3 years.
GPT3 is powerful but blind. The future of Foundation Models will be embodied agents that proactively take actions, endlessly explore the world, and continuously self-improve. What does it take? In our NeurIPS Outstanding Paper “MineDojo”, we provide a blueprint for this future:🧵
5
5 Oct 2022
More incredible work from the #Imagen team @wchan212 @Chitwan_Saharia @jaywhang_ @RuiqiGao @agritsenko @dpkingma @poolio @mo_norouzi @fleet_dj @TimSalimans
5 Oct 2022
Excited to announce Imagen Video, our new text-conditioned video diffusion model that generates 1280x768 24fps HD videos! #ImagenVideo
imagen.research.google/video…
Work w/ @wchan212 @Chitwan_Saharia @jaywhang_ @RuiqiGao @agritsenko @dpkingma @poolio @mo_norouzi @fleet_dj @TimSalimans
2
18 Jul 2022
If you thought the James Webb telescope pics were cool, wait until you see this!
adsp.ai/demos/the-lex-fridma…
🎉 The Lex Fridman Podcast Explorer
🔎 Search over 300 episodes for keywords
👍 Ranked based on Youtube likes and like to view ratio
Comment below your favourite episode!
2
2
4
14 Jul 2022
A bright cold day in April, and the clocks were striking thirteen, digital art #dalle2
1
6 Jul 2022
Love this. Diffusion models are truly beautiful and the future of generative modelling - this is a fantastic tutorial to learn all about them!
6 Jul 2022
New tutorial on keras.io: generating images using denoising diffusion implicit models. Start experimenting with your own image generation models! keras.io/examples/generative…
9
38
17 Apr 2022
My hunch is that it's because the default BatchNormalization momentum is high (0.99) and therefore the global params do not adapt quickly enough in the early stages of training causing the collapse.
David Foster retweeted
13 Apr 2022
Unmodernizing a Jackson Pollock painting with #dalle text diffs
14
86
810
6 Apr 2022
6 Apr 2022
DALL·E 2 — generate any image from a text description. Imagination is the limit.
"A Shiba Inu dog wearing a beret and black turtleneck"
"A photo of a quaint flower shop storefront with a pastel green and clean white facade and open door and big window"
openai.com/dall-e-2/
2
12 Dec 2021
hey @GMJanGustafsson - I'm trying to buy my brother a mug with your face on it for Christmas, but it won't let me ship to the UK through the @chess24com site.
Do you have any spares at home that I could purchase off you? Hope they haven't sold out already 😬
#chess #xmasmiracle
1