Llm Page 408 - DEV Community

Skip to content

DEV Community

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

Nolan Vale

Jul 10

Caching in RAG Systems: What to Cache, What Not To, and Why It Matters More Than You Think

#architecture #llm #performance #rag

3 min read

Arjun Shah

Jun 26

I Built a Prompt Compressor That Saves 65% on LLM Costs — Here's the Story

#ai #llm #opensource #python

2 min read

Mukesh

Jul 30

Testing Non-Deterministic LLM Pipelines in CI: A Contract-Based Approach

#ai #ci #llm #testing

4 min read

Jul 30

How coding agents like Cursor quietly cut input costs by reusing KV states across turns — and what actually breaks the cache

#ai #webdev #llm

4 min read

Jun 26

Cutting our LLM bill ~80% with model routing: the actual cost math

#ai #api #architecture #llm

3 min read

Arjun Shah

Jun 26

SuperCompress: Cut LLM Costs by 65% Without Losing Answers

#showdev #ai #llm #opensource

1 min read

Jun 26

Stop Prompting Your Agents. Start Leading Them.

#ai #agents #llm #leadership

9 min read

kapil Maheshwari

Jun 27

Cutting AI Costs: Batch API for Non-Urgent Workflows

#ai #llm #startup #programming

3 min read

Jul 29

How I Fixed Unpredictable AI Agents With Deterministic Monitoring

#discuss #agents #ai #llm

7 min read

Nolan Vale

Jun 26

Prompt Versioning Is Not Optional in Production. Here Is How to Actually Do It.

#ai #devops #llm #softwareengineering

3 min read

Stacey Schneider

Jun 26

Study: stale documents are RAG poisoning without the attacker

#ai #rag #llm #security

5 min read

pueding

Jun 26

Baidu Unlimited OCR Holds the KV Cache Constant for 40+ Pages: Reference Sliding Window Attention

#ai #llm #machinelearning

8 min read

zeromathai

Jun 26

Why Positional Embeddings Matter — APE, RPE, and RoPE Explained for Developers

#ai #machinelearning #llm #transformers

5 min read

Jul 30

AutoGen's hidden token tax: why a 3-agent chat costs 15 what you expect

#llm #aiagents #python #autogen

5 min read

Jackson Ly

Jul 30

Your cache_read_input_tokens is zero. Here is what silently did it.

#llm #ai #performance #api

5 min read

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