Mastering PyTorch: Create and deploy deep learning models from CNNs to multimodal models, LLMs, and beyond – http://amzn.to/40IFEQR via @PacktDataML #AI #ML #MachineLearning #DataScience #DataScientist #GenAI
GENERATIVE AI
-
Attention Residuals: Novel Architecture for Transformer Models
By
–
Attention Residuals Paper: https://
github.com/MoonshotAI/Att
ention-Residuals/blob/master/Attention_Residuals.pdf
…
Code: https://
github.com/MoonshotAI/Att
ention-Residuals
… -
Attention Residuals: Smart Learned Aggregation in Neural Networks
By
–
Huge! @Kimi_Moonshot presents Attention Residuals (AttnRes)! This new technique replaces fixed accumulation in standard residual connections with smart, learned attention over preceding layer outputs, letting models dynamically aggregate information. Their 'Block AttnRes'
-
ELLIS Board: Florence d’Alché-Buc on AI and Data
By
–
👋 Meet the ELLIS Board This episode features Florence d’Alché-Buc, Professor at @telecomparis 🇫🇷 and ELLIS Board Member. She shares her views on data vs. algorithms, causality, foundation models, and how AI systems should be evaluated. Watch the video: piped.video/kgLCpIUEwiY
-
Excel Game with AI-Powered Formula Engine
By
–
building a working game in excel, with a built-in game AI powered by complex formulas:
-
Human-AI Competition: Humans With AI vs Without AI
By
–
He publicado un episodio en @ivoox
: "#1089: La competición humanos con IA vs humanos sin IA #podcast -
AI Automation Limits: Testing Claude Coworking Chains and Judgment
By
–
my version of 2 is “the stuff that AI just oneshotted, what was the immediate action or thought just before or after you handed over to ai” – for me specifically claude cowork. i end up chaining more and more things and testing the limits of the automation and judgment and
-
C Compiler to LLM Weights and Logarithmic Attention Innovation
By
–
Wait this is so awesome!! Both 1) the C compiler to LLM weights and 2) the logarithmic complexity hard-max attention and its potential generalizations. Inspiring!
-
GPT-5.4 reaches 90% with 32x efficiency improvement in three months
By
–
32× efficiency improvement in just the last 3 months, that's the crazy jump from GPT-5.2 to GPT-5.4! 37 cents/task is essentially almost at human-level efficiency (target was 24 cents/task). This was inconceivable a year ago when o3 cost $4500/task on ARC-AGI-1, 12,000x improved! Jesse🔸⏹️ (@PoliticalKiwi) GPT-5.4 (High) has now cleared 90% on this benchmark at a cost of just $0.37/task So that's a 32x efficiency improvement in the last three months, or 12000x since December 2024 — https://nitter.net/PoliticalKiwi/status/2033142190520905763#m
-
Responsible AI Deployment: Maximizing Benefits and Mitigating Risks
By
–
the focus should be on deploying this tech in a way that maximizes the upsides and mitigates the downsides