🧠 LLM Training - buckman · Scour

RL Scaling Laws for LLMs 🤖LLM Inference

cameronrwolfe.substack.com·6d·Substack

An Empirical Study of Methods for SFTing Opaque Reasoning Models 🛡️LLM Security

lesswrong.com·2d

Fine-tuning Chatterbox on a Low-Resource Language: 7 Things That Mattered 🦙Ollama

dev.to·2h·DEV

Fine-Tuning: the series ⚙️ML Infrastructure

Writing an LLM from scratch, part 32l -- Interventions: updated instruction fine-tuning results 📊LLM Evaluation

gilesthomas.com·5d·Hacker News

DeepSeek open-sources V4 large language model series ⚙️ML Infrastructure

siliconangle.com·2d

Evaluating large language models for accuracy incentivizes hallucinations ⚡Inference

·4d

How to Benchmark LLM Inference Performance: TTFT, ITL, and Throughput Metrics ⚡Inference

dev.to·16h·DEV

Confident and Wrong: We Tested 17 AI Models on Questions a Middle Schooler Could Answer 🧠AI Models

dev.to·22h·DEV

Should We Train Against (CoT) Monitors? 🛡️LLM Security

lesswrong.com·3d

Full Fine-Tuning 🧠Deep Learning

·2d

The Machine Learning Lifecycle: 10 Steps From Problem to Production (And Why Most Projects Fail at Step 3) 👷ML Engineering

dev.to·1d·DEV

How to Fine-Tune Claude on Amazon Bedrock for Your Domain (Complete Guide with Code) 🤖Large Language Models

dev.to·1d·DEV

LoRA 🦙Ollama

·2d

The Fine-Tuning Trap: What the Math Doesn't Tell You About Custom AI Models ✍️Prompt Engineering

dev.to·5d·DEV

Why LLM Agents Fail: Four Mechanisms of Cognitive Decay and the Reasoning Harness Layer 🧠LLM Reasoning

dev.to·1d·DEV

Fine-Tuning LLMs for Legal Tech: Nebius AI Cloud vs Nebius Token Factory — A Developer's Honest Comparison 🦙Ollama

dev.to·5d·DEV

I Fine-Tuned Gemma 4 for LaTeX OCR. The Success Was the Problem. 🤖LLM Inference

dev.to·5d·DEV

RAG Systems in Production: Building Enterprise Knowledge Search 🔗RAG

dev.to·3d·DEV

AI/ML Infrastructure on AWS: A Production-Ready Blueprint ⚙️ML Infrastructure

dev.to·6d·DEV

No more posts from buckman's subscribed feeds.

Scour all 24389 feeds Learn more about Feeds

Log in to enable infinite scrolling