MACHINE LEARNING

→ View original post on X — @antgrasso

Human Talent Drives AI Progress Through Skill Development

By

@antgrasso

–

14 December 2025 15h01

Human talent drives technological progress by supporting skill development, guiding strategic investment, shaping new roles through digital trends, and sustaining growth as advanced capabilities in AI, cybersecurity, and data science expand in value. Microblog by @antgrasso

→ View original post on X — @jeremyphoward

ResNet34 Achieves 94% Accuracy on IIIT Pets Dataset

By

@jeremyphoward

–

14 December 2025 6h20

BTW resnet34 gets 94% accuracy on IIIT Pets after 90s fine-tuning on an old 2080 gaming GPU.

→ View original post on X — @ceobillionaire

Verbalized Sampling: Mitigating Mode Collapse in LLMs

By

@ceobillionaire

–

14 December 2025 4h19

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity Zhang et al.: https://
arxiv.org/abs/2510.01171 #ArtificialIntelligence #DeepLearning #MachineLearning

Encoder vs Decoder: Google and OpenAI’s Architectural Rivalry

By

–

13 December 2025 18h38

I am not sure "OpenAI ran with it" is entirely correct. I remember there was quite some rivalry between Google's encoder approach and OpenAI's push for decoder-style models.
Google tried to make encoder-style models work for many years, since the original architecture.

→ View original post on X — @mit_csail

What Was Your Favorite AI Breakthrough This Year?

By

@mit_csail

–

13 December 2025 18h00

What was your favorite AI breakthrough this year?

DeepSeek V3.2 sparse attention mod overshadows throughput focus announcement

By

–

13 December 2025 16h52

Based on the announcement post it seems the focus is token/sec throughput, cost, and latency. Not sure if that’s because the modeling performance wasn’t exceeding other models or if it was the original plan.
But even then there is now DeepSeek V3.2 with the sparse attention mod.

Sebastian Raschka Updates Comprehensive LLM Architecture Comparison Article

By

–

13 December 2025 15h21

Just updated the Big LLM Architecture Comparison article…
…it grew quite a bit since the initial version in July 2025, more than doubled! https://
magazine.sebastianraschka.com/p/the-big-llm-
architecture-comparison
…

→ View original post on X — @scobleizer

AI knows how I think and analyzes my X feeds

By

@scobleizer

–

13 December 2025 8h47

It knows how I think. Same with you. And it understands our content very deeply. So will be hyper amazing bringing you content. I am playing with AI to analyze my X feeds. See my post on that:

Architectural Variations in Modern Language Models

By

–

13 December 2025 5h46

Yes, they are all relatively related, but usually they have a unique tweak like RMSNorm placement, sliding window, in this case MLA, etc.
I wrote about it in more detail here: