🧠 LLMs - CWhiting · Scour

How AI Works Under the Hood: LLMs Explained with Code 🤖LLM

dev.to·6d·DEV

How to Fine-Tune LLMs on AMD Strix Halo (Ryzen AI MAX+ 395) and Other Exotic AMD Hardware 🤖LLM

promptinjection.net·21h·Hacker News

Two-Tier Verbalization in Natural Language Autoencoders 🤖Large Language Models

openinterp.org·2d·Hacker News

'Current LLMs introduce substantial errors when editing work documents': Microsoft scientists find most AI models struggle with long-running tasks 🤨AI Criticism

·2h

Small Language Models Have a Trillion-Dollar Future ✨Generative AI

hackernoon.com·14h

Recursive Multi-Agent Systems 🤖LLM

recursivemas.github.io·1d·Hacker News

Using Base-LCM to Monitor LLMs 🤖LLM

lesswrong.com·5d

LLMs find the right factors but miss the frame 🤨AI Criticism

ethanfast.com·23h·Hacker News

Unsloth Just Made Fine-Tuning LLMs a Free-Tier Task. 🤖LLM

pub.towardsai.net

·2d

How Large Language Models Work — From Transformers to Conversational AI 🤖Large Language Models

dev.to·17h·DEV

TabPFN-3: scaling foundation models for tabular data to 1M rows 🤖Large Language Models

priorlabs.ai·4h·Hacker News

AutoTTS: Researchers Cut Inference Tokens by 70% by Letting AI Write Its Own Strategy 🧠AI Models

firethering.com·5h·Hacker News

Local Multimodal LLM on iOS with `llama.cpp` (Swift + ObjC++) 🤖LLM

huggingface.co·1d·DEV

Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations 🤖LLM

transformer-circuits.pub·4d·Hacker News

Can a Language Model Paint? 🎨AI Image Generation

etive-mor.com·10h·Hacker News

Training an LLM in Swift, Part 1: Taking matrix multiplication from Gflop/s to Tflop/s 🤖LLM

cocoawithlove.com·2d·Lobsters, Hacker News

I finally found an open-source local LLM that actually competes with cloud AI 🤖GenAI

xda-developers.com·6h

I built the first open benchmark for federal contracting AI. Here's what it shows about frontier LLMs. 🤖LLM

dev.to·5h·DEV

Can LLMs model real-world systems in TLA+? 🤖LLM

sigops.org·5d·Hacker News

Your First Model with AI - Event-Sourced Domain Modeling 🔌MCP

esdm.io·1d·Hacker News

Log in to enable infinite scrolling