🧠 LLMs - aaaaa

🤖ai Blog

iankduncan.com·

Modernizing attendance ticketing in SAS Viya using SAS Agentic AI Accelerator

🔍RAG Blog

blogs.sas.com·

How we fight GPU scarcity without compromise

🧠LLM Inference Blog

equixly.com··Hacker News

Treating LLMs as Programming Books

🤖AI Engineering Blog

jola.dev··Hacker News

Large companies can add a local LLM filter layer to considerably reducing their AI costs

💬NLP

umrashrf.github.io··Hacker News

Fixing a stuck Ollama runner and building a GPU watchdog

🧠LLM Inference

patrickmccanna.net··Hacker News

Large Language Models as Modal Models in Linguistics

🔍RAG Academic

arxiv.org·

BacteReason: A Reasoning Model for Antimicrobial Resistance Prediction

🤖ai Academic

biorxiv.org·

Blogging with an LLM assistant

💬NLP

vincent.bernat.ch··Lobsters, Hacker News

shoo99/paper-rag: A private, fully-local RAG over your own PDFs: BGE-M3 + embedded Qdrant + a local LLM via Ollama. ~150 lines, nothing leaves your machine.

🧠LLM Inference Code

github.com··DEV

How to Defend Against Prompt Injection in Production

🔍RAG Reference

leanpub.com··DEV

LLM AI Chatbots are letting me down every single day

💬NLP

umrashrf.github.io··Hacker News

Report: GKE Inference Gateway delivers up to 92% faster AI responses

🔍RAG Blog

cloud.google.com··Hacker News

An LLM Flagged My Paper About LLMs Flagging Things.

⚙️MLOps

lesswrong.com·

Law Professors Prefer AI over Peer Answers

🤖AI Academic

law.stanford.edu··Hacker News

2x GH200 for LLM inference, Part 2: vLLM, DeepSeek V4 Flash, and MTP

🧠LLM Inference Blog

dnhkng.github.io·

fix(gateway): fail closed for unknown model auth · openclaw/openclaw@85343ea

Ollama 0.30 delivers faster NVIDIA GPU performance and wider hardware support

How I benchmarked a 100% local RAG pipeline to 9/9 (zero API keys)

Show HN: Run Llama.cpp In-Process from Java with Project Panama FFM

What's in the Box? A Field Guide to AI Models

Modernizing attendance ticketing in SAS Viya using SAS Agentic AI Accelerator

How we fight GPU scarcity without compromise

Treating LLMs as Programming Books

Large companies can add a local LLM filter layer to considerably reducing their AI costs

Fixing a stuck Ollama runner and building a GPU watchdog

Large Language Models as Modal Models in Linguistics

BacteReason: A Reasoning Model for Antimicrobial Resistance Prediction

Blogging with an LLM assistant

shoo99/paper-rag: A private, fully-local RAG over your own PDFs: BGE-M3 + embedded Qdrant + a local LLM via Ollama. ~150 lines, nothing leaves your machine.

How to Defend Against Prompt Injection in Production

LLM AI Chatbots are letting me down every single day

Report: GKE Inference Gateway delivers up to 92% faster AI responses

An LLM Flagged My Paper About LLMs Flagging Things.

Law Professors Prefer AI over Peer Answers

2x GH200 for LLM inference, Part 2: vLLM, DeepSeek V4 Flash, and MTP