🧠 LLMs - nitinbansal85.v2.1 · Scour

[AINews] The Inference Inflection ⚙️ML Infra

·1d

Large Language Models are Not Table Saws 🤖AI Agents

agentultra.com·3d·Hacker News

How the Next Generation of AI Models are Going to Completely Change AI Inference 🤖AI

artificialintelligencemadesimple.com·1d

AI hallucinations, bias and data leaks: Expanding LLM risk landscape 🤖AI

devdiscourse.com·2d

Speculative Decoding vs MoE: 3.2x Cost Gap on Llama 3 ⚙️ML Infra

tildalice.io·3d

FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients ⚙️ML Infra

Reiner Pope – The math behind how LLMs are trained and served ⚙️ML Infra

dwarkesh.com·1d·Hacker News

Optimize Anything with LLMs 🚀Performance Engineering

gepa-ai.github.io·6d

Why Model Collapse in LLMs is Inevitable With Self-Learning 🤖AI

hackaday.com·1d·Hacker News

Darwinian Specialization in AI 🤖AI

tomtunguz.com·2d

An Empirical Study of Methods for SFTing Opaque Reasoning Models 🤖AI

lesswrong.com·6d

The Recurrent Transformer: Greater Effective Depth and Efficient Decoding (5 minute read) 🤖AI

alphaxiv.org·2d

MoRFI: Monotonic Sparse Autoencoder Feature Identification ⚙️ML Infra

I build my LLM a Brain 🗄️Database Internals

news.ycombinator.com·3d·Hacker News

Structured Generation for Tool Calling 🗄️Database Internals

blog.dottxt.ai·1d·Hacker News

cauchy221/Alignment-Whack-a-Mole-Code: The official code repo of Alignment Whack-a-Mole: Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models 📚RAG

github.com·23h·Hacker News

A deep dive on AI model distillation attacks ⚙️ML Infra

Google Nested Learning Explained: Hope Architecture, Continual Learning, and the End of Frozen LLMs 🤖AI

aipapersacademy.com·4d

There Will Be a Scientific Theory of Deep Learning 🤖AI

mail.bycloud.ai·1d

The environmental impact of LLMs vs. SLMs 🤖AI

·2d

Sign up or log in to see more results

Log in to enable infinite scrolling