Llm Page 70 - DEV Community

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

Rickesh T N

Sep 5

Temperature 0 is not reproducible. I measured 30 percent of my output changing between identical runs.

#llm #benchmarks #localllm #reproducibility

3 min read

Debapriya Dey

Aug 27

From Guesswork to Evidence: How BotTalk Built a Systematic Approach to AI Model Selection

#ai #aws #llm

4 min read

Rickesh T N

Sep 5

Our 4B beat Claude Opus on a 440K-token corpus. Then it came last on the public benchmark.

#llm #benchmarks #localllm #privateai

4 min read

RAJSHREE

Aug 22

Your RAG Isn't Broken. Your Retrieval Pipeline Is.

#rag #llm #ai #semanticsearch

16 min read

Rickesh T N

Sep 5

I told the model to separate fields with <TAB>. It did exactly that, and I lost 79 percent of my data.

#llm #prompting #debugging #localllm

3 min read

Finley Zhu

Aug 22

Free AI Tokens Are a Trap: An Opinionated Cost Gate for Model Experiments

#ai #llm #python #devops

5 min read

Sam Sun

Aug 22

Free vs Self-Hosted Models: A Break-Even Framework for Agent Workloads

#ai #llm #agents #opensource

5 min read

Riley Wu

Aug 22

Batch LLM Jobs Without Breaking the Bank: A Queue-First Architecture for Free Tiers

#python #llm #architecture #opensource

4 min read

Rickesh T N

Sep 5

A 4B on a 6GB laptop matched frontier-model accuracy on aggregation — except when the answer is a number

#llm #benchmarks #localllm #agents

4 min read

Filippo Pilotta

Aug 22

Why is everyone so skeptical of AI memory tools? Fair question. Here are real answers.

#ai #memory #mcp #llm

5 min read

Weio

Sep 5

How to route LLM requests by task difficulty (a practical guide to cutting API spend without losing quality)

#ai #llm #webdev #programming

5 min read

Morgan Li

Aug 22

Opinion: Free AI Coding Tokens Are a Model Release, Not a Gift

#ai #llm #testing #opinion

5 min read

Vishal Chandak

Aug 22

From Massive to Miniature: How Small Language Models Are Engineered

#smalllanguagemodel #artificialintelligen #machinelearning #llm

12 min read

Casey Sun

Aug 22

Quota Exhaustion Date: A Capacity Calculator for Free Model Quotas

#ai #llm #devops #tutorial

4 min read

Dakota Wu

Aug 22

Why the Most Honest Coding-Agent Evaluation Runs on Free Infrastructure

#ai #agents #testing #llm

5 min read

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