DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Built Two Agent Systems. Each One Proved the Other One Wrong.

I Built Two Agent Systems. Each One Proved the Other One Wrong.

15
Comments 7
3 min read
DNS Tunneling Is Older Than Your Sandbox, and It Just Proved It

DNS Tunneling Is Older Than Your Sandbox, and It Just Proved It

2
Comments 1
3 min read
Retrieval is a routing problem. Your RAG stack just hides it.

Retrieval is a routing problem. Your RAG stack just hides it.

6
Comments 3
4 min read
Designing a Review Interface That Shows Hindsight Memory Working

Designing a Review Interface That Shows Hindsight Memory Working

Comments
5 min read
A Decision Tree for Free-Tier AI Automation: Terms, Branches, Worked Leaves

A Decision Tree for Free-Tier AI Automation: Terms, Branches, Worked Leaves

Comments
5 min read
Streaming Claude Tokens from Bedrock with Node.js 22: SSE Made Simple

Streaming Claude Tokens from Bedrock with Node.js 22: SSE Made Simple

1
Comments
9 min read
I Stole My Own Exam. It Failed the Tool Behind My Own Numbers.

I Stole My Own Exam. It Failed the Tool Behind My Own Numbers.

2
Comments
4 min read
Green Scores Without a Pinned Harness Are Screenshots

Green Scores Without a Pinned Harness Are Screenshots

2
Comments 6
4 min read
How LLMs Learned to Reason: SFT --> RLHF --> RLVR

How LLMs Learned to Reason: SFT --> RLHF --> RLVR

1
Comments 1
8 min read
I Built Five Self-Improving Loops in One Evening. They All Had the Same Bug.

I Built Five Self-Improving Loops in One Evening. They All Had the Same Bug.

Comments
6 min read
Before you pick a hosted agent runtime, check what happens at idle

Before you pick a hosted agent runtime, check what happens at idle

2
Comments 5
5 min read
I Seeded Bugs Into My Own PR to Test the AI Reviewer

I Seeded Bugs Into My Own PR to Test the AI Reviewer

Comments
5 min read
Upgrading Your Embedding Model Doesn't Break RAG Loudly — It Breaks It Quietly

Upgrading Your Embedding Model Doesn't Break RAG Loudly — It Breaks It Quietly

Comments
3 min read
I Asked My Local, Self-Improving AI Agent to Solve a CAPTCHA, what happened was shocking

I Asked My Local, Self-Improving AI Agent to Solve a CAPTCHA, what happened was shocking

Comments 1
5 min read
MCP just went stateless. Here's what the new roadmap builds next.

MCP just went stateless. Here's what the new roadmap builds next.

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