DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Keeping the LLM out of the verdict

Keeping the LLM out of the verdict

Comments 1
5 min read
One Endpoint, Your Whole Toolchain: Running Chinese Frontier Models in Claude Code, Cursor, Cline, Aider and More

One Endpoint, Your Whole Toolchain: Running Chinese Frontier Models in Claude Code, Cursor, Cline, Aider and More

Comments
4 min read
AI Agent Architecture 2026: Building Production-Grade Systems — Patterns, Benchmarks, and Lessons from 10,000-Agent Swarms

AI Agent Architecture 2026: Building Production-Grade Systems — Patterns, Benchmarks, and Lessons from 10,000-Agent Swarms

7
Comments 1
19 min read
300+ languages doesn't mean what you think: three tiers of code understanding

300+ languages doesn't mean what you think: three tiers of code understanding

Comments
7 min read
How parallel AI agents should talk to each other (and the bug that proved it)

How parallel AI agents should talk to each other (and the bug that proved it)

1
Comments 2
3 min read
I Shipped a Fix That Fixed Nothing. Here's Why I Kept It.

I Shipped a Fix That Fixed Nothing. Here's Why I Kept It.

20
Comments 3
10 min read
I Assumed My Retriever Failed at Stage One. The Bigger Failure Was at Stage Three.

I Assumed My Retriever Failed at Stage One. The Bigger Failure Was at Stage Three.

Comments
3 min read
I tried to patch a blind spot in my own MCP tool. The patch and a false-positive bug cancel out.

I tried to patch a blind spot in my own MCP tool. The patch and a false-positive bug cancel out.

2
Comments
5 min read
I built an async wrapper for OpenAI/Anthropic SDKs because I didn't want a proxy in my request path

I built an async wrapper for OpenAI/Anthropic SDKs because I didn't want a proxy in my request path

Comments
2 min read
I created a tool to inspect full python codebases

I created a tool to inspect full python codebases

Comments
1 min read
AI Will Be Wrong Sometimes. What Then?

AI Will Be Wrong Sometimes. What Then?

Comments 1
3 min read
Why AI agent isolation breaks from the inside

Why AI agent isolation breaks from the inside

Comments 3
4 min read
When your benchmark is wrong and your model is right

When your benchmark is wrong and your model is right

1
Comments
7 min read
"How to Tell If an LLM Was Really Trained From Scratch: A Reproducible Fingerprinting Method"

"How to Tell If an LLM Was Really Trained From Scratch: A Reproducible Fingerprinting Method"

Comments
7 min read
I tested if system prompts actually matter, here's what I found

I tested if system prompts actually matter, here's what I found

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