close

DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why does everything in an agent go through the LLM?

Why does everything in an agent go through the LLM?

BERJAYA 2
Comments 7
4 min read
Killed by the Word 'git': One Token of Coincidence, 40 Points of Pass Rate

Killed by the Word 'git': One Token of Coincidence, 40 Points of Pass Rate

BERJAYA BERJAYA BERJAYA 15
Comments 4
8 min read
Why I Ditched "Just Let the LLM Handle It" for a State Machine (And Slept Better at Night)

Why I Ditched "Just Let the LLM Handle It" for a State Machine (And Slept Better at Night)

BERJAYA 2
Comments 3
3 min read
MTP in Practice: Benchmarking Gemma's Speculative Decoding on a Real GPU

MTP in Practice: Benchmarking Gemma's Speculative Decoding on a Real GPU

Comments
13 min read
Keep the LLM Out of the Math: Deterministic Boundaries for Financial Modelling Agents

Keep the LLM Out of the Math: Deterministic Boundaries for Financial Modelling Agents

Comments
11 min read
Anthropic shipped an official eval runner for Claude Code. I made my tool run on it the same day. Field notes.

Anthropic shipped an official eval runner for Claude Code. I made my tool run on it the same day. Field notes.

Comments 2
3 min read
What Is an Agent Harness? Harness Engineering Explained

What Is an Agent Harness? Harness Engineering Explained

BERJAYA BERJAYA BERJAYA 5
Comments 11
12 min read
Three AI Agents Corrected Each Other. None of Them Were Talking.

Three AI Agents Corrected Each Other. None of Them Were Talking.

BERJAYA 1
Comments 3
7 min read
10 SDLC Checks AI Will Skip Unless You Make Them a Gate

10 SDLC Checks AI Will Skip Unless You Make Them a Gate

BERJAYA BERJAYA BERJAYA 20
Comments 5
6 min read
AI agent or plain automation: where the real ROI is

AI agent or plain automation: where the real ROI is

Comments
5 min read
I Added More AI Agents to the Problem. Nothing Changed.

I Added More AI Agents to the Problem. Nothing Changed.

BERJAYA 1
Comments 2
4 min read
Indirect prompt injection in a RAG pipeline: one attack, step by step, and what actually stopped it

Indirect prompt injection in a RAG pipeline: one attack, step by step, and what actually stopped it

BERJAYA 1
Comments 3
5 min read
How many tools should an MCP server have?

How many tools should an MCP server have?

BERJAYA 1
Comments 7
5 min read
AI Weekly — 2026-09-04 to 2026-09-11 | Open-weight races collide with closed-frontier launches

AI Weekly — 2026-09-04 to 2026-09-11 | Open-weight races collide with closed-frontier launches

Comments
7 min read
SENTINEL-RL for SOCs: Architectural Gains and Cost Realities from Decoupling Semantic and Topological Reasoning

SENTINEL-RL for SOCs: Architectural Gains and Cost Realities from Decoupling Semantic and Topological Reasoning

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