DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Will software ever be free?

Will software ever be free?

3
Comments 1
1 min read
The Problem of Machine Amnesia: Moving from Context Windows to Persistent State

The Problem of Machine Amnesia: Moving from Context Windows to Persistent State

Comments
3 min read
Event-Driven AI: How Kafka Streams Changed the Way We Run LLMs in Production

Event-Driven AI: How Kafka Streams Changed the Way We Run LLMs in Production

Comments
15 min read
Why I Stopped Using JSON Tool-Calling for My Coding Agent

Why I Stopped Using JSON Tool-Calling for My Coding Agent

Comments
3 min read
Automating Enterprise Sales With Salesgraph: Real ROI, Real Failure Cases

Automating Enterprise Sales With Salesgraph: Real ROI, Real Failure Cases

Comments
5 min read
3 Costly Mistakes I Made With the OpenAI API (So You Don't Have To)

3 Costly Mistakes I Made With the OpenAI API (So You Don't Have To)

Comments
2 min read
Grok 4.6 Is Now in Foundry — Here’s What It Means If You Write C#

Grok 4.6 Is Now in Foundry — Here’s What It Means If You Write C#

1
Comments 1
14 min read
Gemini reads the floor plan. Code decides what it means.

Gemini reads the floor plan. Code decides what it means.

Comments
5 min read
RAG Without the Hype: Make Retrieval Observable, Testable, and Replaceable

RAG Without the Hype: Make Retrieval Observable, Testable, and Replaceable

2
Comments 2
3 min read
Every LLM Request Has Two Halves. Only One Uses Your GPU Cores

Every LLM Request Has Two Halves. Only One Uses Your GPU Cores

Comments
6 min read
No one measured AI API latency and uptime independently across regions — so I built it. 38 days and 2M probes in, here's what the data shows

No one measured AI API latency and uptime independently across regions — so I built it. 38 days and 2M probes in, here's what the data shows

Comments
3 min read
I Built an Agentic Hybrid RAG System with FAISS and BM25

I Built an Agentic Hybrid RAG System with FAISS and BM25

1
Comments
4 min read
Autoregressive vs Diffusion LLMs: How the Next Generation of Language Models Actually Writes Text

Autoregressive vs Diffusion LLMs: How the Next Generation of Language Models Actually Writes Text

Comments
8 min read
My board never scored an outage as a regression. My evidence couldn't prove it.

My board never scored an outage as a regression. My evidence couldn't prove it.

Comments
5 min read
Free Model Meets Free Server: Designing a Repeatable Reliability Experiment

Free Model Meets Free Server: Designing a Repeatable Reliability Experiment

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