DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Context Engineering: The Skill Replacing Prompt Engineering in 2026

Context Engineering: The Skill Replacing Prompt Engineering in 2026

1
Comments
4 min read
We May Be Building AI Development Tools Backwards

We May Be Building AI Development Tools Backwards

Comments
1 min read
Building a production RAG across a Book series: Retrieval, Reranking, and Hard Lessons

Building a production RAG across a Book series: Retrieval, Reranking, and Hard Lessons

3
Comments
7 min read
Anthropic and the Runtime Harness for Persistent Agents

Anthropic and the Runtime Harness for Persistent Agents

Comments
4 min read
Beyond the Hype: The Real State of AI in Data Analysis and LLMs (2025-2026)

Beyond the Hype: The Real State of AI in Data Analysis and LLMs (2025-2026)

1
Comments 1
7 min read
LLM Study Diary #1: Transformer

LLM Study Diary #1: Transformer

2
Comments
3 min read
How I Used DSPy to Cut Claude API Costs by 73% (With Real Benchmarks)

How I Used DSPy to Cut Claude API Costs by 73% (With Real Benchmarks)

Comments
4 min read
Evaluating LLMs for Under a Dollar

Evaluating LLMs for Under a Dollar

2
Comments
4 min read
This is why grep is failure when it comes to quality and token saving!

This is why grep is failure when it comes to quality and token saving!

2
Comments
1 min read
I stopped letting AI review its own code

I stopped letting AI review its own code

Comments 1
6 min read
I fine-tuned an LLM for a client, then told them not to use it

I fine-tuned an LLM for a client, then told them not to use it

1
Comments
5 min read
I built a local-first AI memory layer for LLMs in Rust (no cloud, no API keys)

I built a local-first AI memory layer for LLMs in Rust (no cloud, no API keys)

Comments 3
1 min read
LangChain fundamentals part 2: structured outputs and tool calling

LangChain fundamentals part 2: structured outputs and tool calling

Comments
2 min read
KVQuant: Run 70B LLMs on 8GB RAM with KV Cache Quantization

KVQuant: Run 70B LLMs on 8GB RAM with KV Cache Quantization

Comments
1 min read
Building a Persistent Knowledge Base RAG System with FastAPI, llama.cpp, Chroma, and Open WebUI

Building a Persistent Knowledge Base RAG System with FastAPI, llama.cpp, Chroma, and Open WebUI

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