Llm Page 109 - DEV Community

Skip to content

DEV Community

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

Metal Mods

Sep 22

Treat streamed LLM output as an uncommitted draft

#ai #startup #llm

4 min read

Oct 5

Where AI agent test cases come from: synthetic vs. production data

#agents #ai #llm #evals

4 min read

Sep 22

GRPO: How Language Models Learn to Reason

#ai #llm #machinelearning

4 min read

Sep 22

Our task categorizer routed 46% of tasks. A $0.04/MTok decision model routes 97%.

#benchmarks #categorization #embeddings #llm

3 min read

Sep 26

Why Is Jev So Fast Compared to Traditional LLMs?

#ai #architecture #llm #performance

3 min read

Sep 22

94.7% on LoCoMo — and why most of the gap between published memory numbers isn't the memory

#memory #benchmarks #agents #llm

9 min read

MD Faiz

Sep 22

I went through 14 reports of AI agents burning money. Every budget that failed, failed one of two ways.

#ai #python #llm #programming

2 min read

Rost

Sep 22

Mnemosyne for Hermes Agent: Local Memory Quickstart

#hermes #ai #llm #architecture

9 min read

Sep 22

We Thought the LLM Was Wrong. Our Safety Detector Was Wrong.

#ai #programming #llm #detector

1 min read

Himanshu Kawale

Sep 22

5 Guardrails That Keep an LLM Agent Shippable in Production

#ai #llm #agents #webdev

2 min read

Marc

Sep 22

Your AI eval is green because it never called the model

#ai #llm #typescript #testing

6 min read

Sep 22

THIS AI MODEL DOESN'T WANT TO TALK TO YOU

#ai #jev #llm #programming

22 min read

Sep 22

How to reduce LLM costs in production: 07 techniques you need to know

#llm #ai #genai #devops

3 min read

Antonio Lopes Correia

Sep 26

How Do You Know When AI Is Wrong? The Case for Evals.

#ai #testing #softwareengineering #llm

6 min read

Francisco Riveros

Sep 22

Beyond Autoregression: Running JEV and Open "System 1" Decision Models on Google Cloud

#ai #cloud #llm #machinelearning

10 min read

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