DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Span attributes that catch LLM cost regressions before billing does

Span attributes that catch LLM cost regressions before billing does

Comments
1 min read
Rasengan v1.2.2 - Error overlay, LLM support & agent skills

Rasengan v1.2.2 - Error overlay, LLM support & agent skills

Comments
1 min read
How to Evaluate LLM Output Quality Programmatically

How to Evaluate LLM Output Quality Programmatically

1
Comments
5 min read
I let Claude and Codex argue about my code for a week. Here's what they caught.

I let Claude and Codex argue about my code for a week. Here's what they caught.

Comments
5 min read
Claude Fable 5 is currently unavailable , here's what actually happened

Claude Fable 5 is currently unavailable , here's what actually happened

Comments 1
2 min read
How to Cheat LLM Context: A Lightweight AI Doc Assistant Architecture

How to Cheat LLM Context: A Lightweight AI Doc Assistant Architecture

2
Comments
3 min read
Lum1104 — Understand-Anything

Lum1104 — Understand-Anything

Comments
3 min read
Stop Writing Bigger Prompts. Start Writing Better Task Contracts

Stop Writing Bigger Prompts. Start Writing Better Task Contracts

2
Comments 1
5 min read
Hermes Agent: First Contact

Hermes Agent: First Contact

Comments
5 min read
I kept rewriting the same quiz + spaced-repetition code. So I packaged it into an API.

I kept rewriting the same quiz + spaced-repetition code. So I packaged it into an API.

Comments
1 min read
Why AI Agents Forget by Design

Why AI Agents Forget by Design

3
Comments
12 min read
I built Huiyu Pi — a self-hosted AI coding agent that starts at ~80 tokens.

I built Huiyu Pi — a self-hosted AI coding agent that starts at ~80 tokens.

Comments
1 min read
GrepSeek Trains a Search Agent to Use Shell Commands: GRPO-Trained Shell-Command Search

GrepSeek Trains a Search Agent to Use Shell Commands: GRPO-Trained Shell-Command Search

Comments
6 min read
GPT-5.6 Is Real (a Codex Log Says So) — Everything Else Is Made Up

GPT-5.6 Is Real (a Codex Log Says So) — Everything Else Is Made Up

3
Comments
6 min read
Self-Hosted AI Risk Gate in 10 Minutes: Meet ITTE – Your Pre-Deploy Risk Brain with Self-Evolving Memory

Self-Hosted AI Risk Gate in 10 Minutes: Meet ITTE – Your Pre-Deploy Risk Brain with Self-Evolving Memory

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