First screen, captured .
Looks similar
Miniature Macintosh with Raspberry Pi(hackster.io)
116 points by rcarmo | 42 comments
TabPFN and TabICL vs. tuned XGBoost: the model that doesn't train won 14/14(efraingaray.com)
21 points by EfrainGaray | 9 comments
Blog post benchmarking TabPFN and TabICL foundation models against tuned XGBoost on fourteen tabular datasets, finding the no-training models won all fourteen.
Related stories
TurboQuant: Redefining AI efficiency with extreme compression(research.google)
495 points by ray__ | 134 comments
Google Research blog post introducing TurboQuant, a method for extreme compression to improve AI model efficiency.
Deep Learning Is Applied Topology(theahura.substack.com)
473 points by theahura | 176 comments
A Substack essay from 12 Grams of Carbon arguing that deep learning is applied topology, explaining how neural networks transform data lying on manifolds.
The Little Book of Deep Learning [pdf](fleuret.org)
420 points by dataminer | 29 comments
A PDF of François Fleuret's The Little Book of Deep Learning, a short introductory textbook on deep learning.
Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning(techcommunity.microsoft.com)
399 points by lappa | 136 comments
Microsoft AI Platform Blog post announcing Phi-4, a small language model specializing in complex reasoning.
Deep learning gets the glory, deep fact checking gets ignored(rachel.fast.ai)
549 points by chmaynard | 134 comments
Rachel Thomas blog post on how a high-profile Nature paper using a Transformer to predict enzyme functions contained many errors that received far less attention than the original result.
AI models can provably hide arbitrary capabilities(arxiv.org)
252 points by sbulaev | 118 comments
An arXiv paper showing AI models can embed encrypted neural network backdoors that provably hide arbitrary capabilities from elicitation-based safety evaluations.