🤖 LLM - CWhiting · Scour

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

dev.to·5h·DEV

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

ethanfast.com·11h·Hacker News

Using Base-LCM to Monitor LLMs 🧠LLMs

lesswrong.com·5d

Adola: Reducing LLM input tokens by 70% 🧠LLMs

adola.app·2d·Hacker News

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

pub.towardsai.net

·2d

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

til.simonwillison.net·11h·Hacker News

China LLM Aggregation API 🧠LLMs

chinawhapi.com·3h·DEV

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·1d·Lobsters, Hacker News

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

castform.com·9h·Hacker News

ReFlect: Training-Free Error Recovery for Long-Horizon LLM Reasoning 🧠LLMs

dev.to·17h·DEV

WriteHybrid – Humanize AI text and bypass detection with natural writing ✨Generative AI

betalist.com·2h

Article: What are LLMs and Generative AI good at 🤖GenAI

jackpritz.com·2d·Hacker News

SubQ: a sub-quadratic LLM with 12M-token context 🤖Large Language Models

subq.ai·6d·Hacker News

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

promptinjection.net·10h·Hacker News

AEndrix03/Graft: Local-first semantic cache for AI agents. A small C daemon + CLI that remembers what your agent learned across sessions. Plugs into Claude Code, Codex, Gemini CLI, and Claude Desktop / ChatGPT via MCP. No LLM calls, no SaaS, no API key. 💻Codex

github.com·5h·Hacker News

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

howtogeek.com·1d

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

huggingface.co·18h·DEV

Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners 🧠AI Models

botcs.github.io·1h·Hacker News

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

krithik.xyz·3d·Hacker News

Log in to enable infinite scrolling