DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Keeping a client's VLM inference inside the EU with a self-hosted-first gateway
marcorinaldi_ai profile

Keeping a client's VLM inference inside the EU with a self-hosted-first gateway

#machinelearning #llm #infrastructure #computervision
Comments
4 min read
The latency tax of an LLM gateway: I measured Bifrost's overhead
marcuswwchen profile

The latency tax of an LLM gateway: I measured Bifrost's overhead

#mlops #llm #infrastructure #machinelearning
Comments
4 min read
LLM Self-Preference Bias: How Anonymized Peer Review Fixes It
praveenlavu profile

LLM Self-Preference Bias: How Anonymized Peer Review Fixes It

#ai #llm #machinelearning #nlp
Comments
7 min read
Drift Detection for LLM Routing: Catching Silent Model Degradation
praveenlavu profile

Drift Detection for LLM Routing: Catching Silent Model Degradation

#architecture #llm #machinelearning #monitoring
Comments
8 min read
The Citation Lied Without Lying: The Hard Limit of My Memory Gate

Publicly pre-registered failure predictions
kenielzep97 profile

The Citation Lied Without Lying: The Hard Limit of My Memory Gate

#agents #ai #llm #softwareengineering
18
Comments 119
8 min read
GLM Is the New Hotness, So Let's Test It On the Homelab
carryologist profile
Rob

GLM Is the New Hotness, So Let's Test It On the Homelab

#modelshowdown #benchmark #ai #llm
Comments 3
11 min read
Building a RAG Pipeline From Scratch: What SmartQueue Taught Me About Retrieval
ambarish_0221 profile

Building a RAG Pipeline From Scratch: What SmartQueue Taught Me About Retrieval

#rag #llm #python #ai
2
Comments
6 min read
Bigger Context Windows Didn't Make Our RAG Smarter

Keyword density vs original decision logic
valerykot profile

Bigger Context Windows Didn't Make Our RAG Smarter

#ai #llm #machinelearning #rag
22
Comments 42
2 min read
Two queues for local-LLM fleets
praveenlavu profile

Two queues for local-LLM fleets

#ai #llm #performance #systemdesign
Comments
7 min read
LLMs didn't kill feature engineering. Engineers did.
jignesh_maheshwari_93e21d profile

LLMs didn't kill feature engineering. Engineers did.

#ai #machinelearning #llm #programming
4
Comments 2
3 min read
How I built a 3-provider LLM fallback system in production (and what actually broke)
ayush_notsogreat_b673d5 profile

How I built a 3-provider LLM fallback system in production (and what actually broke)

#llm #python #webdev #ai
2
Comments
7 min read
AIchain Tools: Search, Conversion, Embeddings
yait profile
YAIT

AIchain Tools: Search, Conversion, Embeddings

#ai #llm #tooling #tutorial
Comments
6 min read
Benchmarking LLMs for Coding in 2026: A Practical Guide
mrclaw207 profile

Benchmarking LLMs for Coding in 2026: A Practical Guide

#ai #llm #agents #llmtools
Comments
3 min read
Unlocking Local LLM Power with Ollama: A Practical Guide
yogiravi_2003 profile

Unlocking Local LLM Power with Ollama: A Practical Guide

#ollama #llm #ai #opensource
1
Comments
3 min read
Compiling the Process, Not the Code: a machine-checked workflow for coding agents
vasyltretiakov profile

Compiling the Process, Not the Code: a machine-checked workflow for coding agents

#ai #llm #programming #agents
Comments
10 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.