Announcing the Open Canvas Working Group (OCWG).
Building atop @obsmd's JSON Canvas, we will work to establish a robust file format to enable interoperability between infinite canvas tools.
Participants: @tldraw, @excalidraw, @statelyai, @KinopioClub, @dxos_org, and others
1/n
Still seeing rounds of layoffs over here. If you're a Unity / C# developer interested in multiplayer, come work with us at Normal!
RT's appreciated!
https://t.co/2zQS46UTEe
Did you MISS this workshop I put together last year?
Well, here's to the second chances! 🥂
Get my FREE investing workshop and learn how to grow your portfolio to 7-figures+ 💸
Simply like + retweet and I will send you DM!
Let's go!
New Paper Out.
Evolutionary Optimization of Model Merging Recipes
https://t.co/kn75wPgrtQ
Our goal is not about training any particular individual foundation model. Instead, we think it makes more sense to create the machinery to automatically generate foundation models for us!
Brand new trailer of "Dan Da Dan" anime series by Fuga Yamashiro & Science Saru studio (Scott Pilgrim, Devilman Crybaby).
Based on Yukinobu Tatsu's manga.
Full video >> https://t.co/hkDpGg2id9
We live in such strange times. Apple, a company famous for its secrecy, published a paper with staggering amount of details on their multimodal foundation model. Those who are supposed to be open are now wayyy less than Apple.
MM1 is a treasure trove of analysis. They discuss lots of architecture designs and even disclose that they train on GPT-4V-generated data. They provide exact scaling law coefficients (to 4 significant figures), MoE settings, and even optimal learning rate functions.
I have not seen this level of details from a big tech's whitepaper for a very, very long time. Apple's so back!