🤖 LLM - CWhiting · Scour

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

dev.to·16h·DEV

Building Safe LangChain Agents with Scope Verification 🔌MCP

scopegate.ai·2h·DEV

Using Base-LCM to Monitor LLMs 🧠LLMs

lesswrong.com·5d

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

pub.towardsai.net

·2d

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

ethanfast.com·22h·Hacker News

Useful Memories Become Faulty When Continuously Updated by LLMs 🧠LLMs

dylanzsz.github.io·1d·Hacker News

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

xda-developers.com·5h

Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations 🧠LLMs

transformer-circuits.pub·4d·Hacker News

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

cocoawithlove.com·2d·Lobsters, Hacker News

Using LLM in the shebang line of a script 🔌Claude Plugins

til.simonwillison.net·22h·Hacker News

Auto-Merging RAG: Hierarchical Retrieval ⛓️ 🤖Large Language Models

dev.to·23h·DEV

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

firethering.com·4h·Hacker News

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

huggingface.co·1d·DEV

Adola: Reducing LLM input tokens by 70% 🧠LLMs

adola.app·3d·Hacker News, Hacker News

China LLM Aggregation API 🧠LLMs

chinawhapi.com·14h·DEV

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

·1h

I used Gemini, ChatGPT, and Claude to summarize a 121-page PDF and one crushed the others 💻AI Coding

howtogeek.com·2d

Prompt caching but for RL – 7.5x speedup on long-prompt/short-response workloads ✍️Prompt Engineering

castform.com·19h·Hacker News

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

dev.to·4h·DEV

Tracing tokens through Llama 3.1 8B inference on H100s 🧠LLMs

krithik.xyz·3d·Hacker News

Log in to enable infinite scrolling