DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
We stopped writing eval cases by hand. Now every prod incident becomes one.

We stopped writing eval cases by hand. Now every prod incident becomes one.

Comments
2 min read
PII Redaction Built Entirely in the Browser

PII Redaction Built Entirely in the Browser

4
Comments 4
2 min read
AI Agentic Workflow Explained: A Quick Tour of Harness, Tools, Skills, MCP, and Memory

AI Agentic Workflow Explained: A Quick Tour of Harness, Tools, Skills, MCP, and Memory

2
Comments
5 min read
Clioloop — The Open-Source AI Agent with Agentic Fusion

Clioloop — The Open-Source AI Agent with Agentic Fusion

2
Comments
2 min read
Is Your AI Agent Production-Ready? Define the Bar First

Is Your AI Agent Production-Ready? Define the Bar First

Comments
3 min read
Eval-Gated AI Releases: Treating Retrieval Quality Like Unit Tests

Eval-Gated AI Releases: Treating Retrieval Quality Like Unit Tests

1
Comments 1
2 min read
Distinguishing wrong from absent

Distinguishing wrong from absent

Comments 2
1 min read
Keeping a client's VLM inference inside the EU with a self-hosted-first gateway

Keeping a client's VLM inference inside the EU with a self-hosted-first gateway

Comments
4 min read
The latency tax of an LLM gateway: I measured Bifrost's overhead

The latency tax of an LLM gateway: I measured Bifrost's overhead

Comments
4 min read
Running Qwen3 Through the ExecuTorch MLX Delegate: Up to 4.52x Faster on M1 Max

Running Qwen3 Through the ExecuTorch MLX Delegate: Up to 4.52x Faster on M1 Max

Comments
7 min read
Autonomy Is the Bug: Why Self-Driving Agents Hallucinate When the Model Barely Does

Autonomy Is the Bug: Why Self-Driving Agents Hallucinate When the Model Barely Does

6
Comments 6
8 min read
GLM Is the New Hotness, So Let's Test It On the Homelab

GLM Is the New Hotness, So Let's Test It On the Homelab

Comments 3
11 min read
We got tired of stuffing our AI agent's entire chat history into every prompt, so we built an API that doesn't

We got tired of stuffing our AI agent's entire chat history into every prompt, so we built an API that doesn't

Comments 6
1 min read
Building a RAG Pipeline From Scratch: What SmartQueue Taught Me About Retrieval

Building a RAG Pipeline From Scratch: What SmartQueue Taught Me About Retrieval

2
Comments
6 min read
Bigger Context Windows Didn't Make Our RAG Smarter

Keyword density vs original decision logic

Bigger Context Windows Didn't Make Our RAG Smarter

22
Comments 42
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.