DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Tigergraph Hackathon

Tigergraph Hackathon

Comments
4 min read
How to A/B Test LLM Prompts Without Breaking Production

How to A/B Test LLM Prompts Without Breaking Production

1
Comments 1
5 min read
Choosing AI Paths, Boosting Bots, Triple AI Wins, Browser Controls, and a $0.41/Day AI Employee

Choosing AI Paths, Boosting Bots, Triple AI Wins, Browser Controls, and a $0.41/Day AI Employee

Comments
2 min read
Day 13 of 60: Today I Started Learning RAG

Day 13 of 60: Today I Started Learning RAG

Comments
2 min read
The Hidden Cost of AI Agents: Why Your LLM Pipeline Is Bleeding Money

The Hidden Cost of AI Agents: Why Your LLM Pipeline Is Bleeding Money

Comments 1
5 min read
Speculative decoding shifted our output distribution and evals missed it

Speculative decoding shifted our output distribution and evals missed it

1
Comments 1
4 min read
I built a Homebrew for AI skills: install flow and eval harness inside

I built a Homebrew for AI skills: install flow and eval harness inside

3
Comments
8 min read
How to Extract Business Rules from Legacy COBOL Code

How to Extract Business Rules from Legacy COBOL Code

Comments
8 min read
How I Reduced Prompt Injection Attacks by 86% With My Own Framework (And What Went Wrong the First Time)

How I Reduced Prompt Injection Attacks by 86% With My Own Framework (And What Went Wrong the First Time)

Comments
5 min read
Push vs Pull Memory: A Better Way to Think About AI Agent Memory

Push vs Pull Memory: A Better Way to Think About AI Agent Memory

1
Comments 1
5 min read
Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift

Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift

1
Comments
5 min read
Claude Code and Codex are logging your token usage locally. Here is how to read it.

Claude Code and Codex are logging your token usage locally. Here is how to read it.

Comments
3 min read
RAG SOTA: I Tested 7 Pipelines and Built SEQUOIA (Open Source)

RAG SOTA: I Tested 7 Pipelines and Built SEQUOIA (Open Source)

Comments 2
2 min read
Is AI Getting Quietly Dumber? A 24/7 Benchmark That Catches LLM Degradation

Is AI Getting Quietly Dumber? A 24/7 Benchmark That Catches LLM Degradation

Comments 2
6 min read
Your LLM bill is not your capacity plan. Here's the math that pages you at 2am.

Your LLM bill is not your capacity plan. Here's the math that pages you at 2am.

Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.