Llm Page 63 - DEV Community

Skip to content

DEV Community

👋 Sign in for the ability to sort posts by relevant, latest, or top.

TANDIU

Oct 26

One price change, two new models, 170+ funding rounds: TANDIU weekly data notes (Oct 19–25, 2026)

#ai #llm #mcp #opendata

4 min read

skvrtyk

Oct 25

Your Eval Suite Has a Flake Rate: Gating LLM Changes on Paired, Powered Tests

#ai #llm #devops #python

3 min read

jidonglab

Oct 30

vLLM Speculative Decoding: 1.8x Faster Alone, Slower at 32 Users

#llm #performance #machinelearning #python

7 min read

Oct 30

How to Evaluate a RAG Chatbot Before Your Customers Do: Build a Test Set That Catches Real Failures

#ai #rag #llm #testing

6 min read

Nirali for Toolbit AI

Oct 26

Prompt Caching Cost Is What Decides Your AI Coding Agent Bill

#discuss #ai #llm #agents

6 min read

frank chu

Oct 26

I built Karpathy's LLM Wiki as a product — the hard part was stopping the LLM from writing

#showdev #ai #llm #tools

7 min read

Nirali

Oct 26

Open-Weight AI Models You Can Run Yourself: October 2026 Edition

#ai #llm #opensource #machinelearning

8 min read

Miracle

Oct 26

If the Model Can Write a Better Sentence, Whose Sentence Is It?

#ai #llm #writing

4 min read

Pesimmoq

Oct 26

LiteLLM 1.107.0 was malware. A 5-minute check for AI developers, and the one-line setting that would have skipped it

#python #security #ai #llm

5 min read

AI Bug Slayer 🐞

Oct 26

I Talked to 20 AI Engineers This Month. Here's What They're All Worried About

#aiagents #ai #llm #webdev

4 min read

AI Bug Slayer 🐞

Oct 26

I Built the Same AI Agent in 4 Frameworks. Here's the Honest Breakdown.

#aiagents #ai #llm #webdev

4 min read

skvrtyk

Oct 26

Context Assembly Is a Build Step: Versioning the Prompt You Actually Send

#ai #llm #devops #python

3 min read

Oct 25

Structured outputs that do not break: schemas, Zod and a repair retry

#ai #typescript #llm #webdev

8 min read

Vibhu for Cairn

Oct 26

A governed fine-tune for $0.86: Qwen3-4B on IFC/BIM, with a person approving every step

#ai #llm #machinelearning #opensource

4 min read

Oct 25

Evals before prompts: a small eval harness for an LLM feature

#ai #llm #evals #testing

9 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.