Perplexity Computer wins hands down over Claude Code and Codex, even with their latest versions. The outputs are 5x-10x better for some use cases. @perplexity_ai – can you please launch a desktop app and a CLI? [Translated from EN to English]
Pretrain Vision and LLMs (Large Language Models) in Python — Techniques for Building & Deploying Foundation Models on AWS: http://
amzn.to/3pT9seD v/ @PacktDataML ————
#AI #MachineLearning #MLOps #DataScience #ComputerVision #DataScientist #GenAI
Scikit-learn Cookbook — 80+ recipes for #MachineLearning in Python with scikit-learn [3rd Edition]: http://
amzn.to/4oDGOq7 v/ @PacktDataML 𝓒𝓸𝓷𝓽𝓮𝓷𝓽𝓼:
Common Conventions & API Elements of Scikit-Learn
Pre-Model Workflow and Data Preprocessing
Dimensionality
if there's a specific style you like from v7 you can try bringing it into v8 by using the old v7 image as a style reference. if you can tell us the prompt we can look at it with our team too! <3
Oh wow, Mamba-3 is here! For me, the most interesting use case of Mamba and Mamba-likes are the recent transformer attention hybrid architectures (Qwen3.5, Kimi Linear, etc.) Would be interesting to swap Gated DeltaNet with Mamba-3 (which now also has RoPE) in next gen hybrids. Albert Gu (@_albertgu) The newest model in the Mamba series is finally here 🐍 Hybrid models have become increasingly popular, raising the importance of designing the next generation of linear models. We've introduced several SSM-centric ideas to significantly increase Mamba-2's modeling capabilities without compromising on speed. The resulting Mamba-3 model has noticeable performance gains over the most popular previous linear models (such as Mamba-2 and Gated DeltaNet) at all sizes. This is the first Mamba that was student led: all credit to @aakash_lahoti @kevinyli_ @_berlinchen @caitWW9, and of course @tri_dao! — https://nitter.net/_albertgu/status/2033948415139451045#m
I don't appreciate the snarkiness at the end when I'm engaging with you honestly and in good faith. I'll refer you to the post tomorrow, and point out that any author (senior or otherwise) of >= 4 submissions *must* review ("Reciprocal reviewing" on https://
icml.cc/Conferences/20
26/PeerReviewFAQ
…)