DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Thinking On or Off? Gemma 4 E4B on an 8 GB RTX 3050

Drafters double speed without hurting accuracy

Thinking On or Off? Gemma 4 E4B on an 8 GB RTX 3050

16
Comments 6
9 min read
Is an Uncensored AI a Better Pentester? I Tested 3 Models

Is an Uncensored AI a Better Pentester? I Tested 3 Models

Comments
9 min read
Your Code Never Names a Model. It Still Calls a Retired One.

Your Code Never Names a Model. It Still Calls a Retired One.

Comments
5 min read
Evaluating an LLM Feature Before Launch: A Practical Guide

Evaluating an LLM Feature Before Launch: A Practical Guide

Comments 1
9 min read
Test AI outputs by properties, not by one golden string

Test AI outputs by properties, not by one golden string

Comments
5 min read
How to Catch a Coding Agent That Fakes Passing Tests

How to Catch a Coding Agent That Fakes Passing Tests

Comments
3 min read
Cutting 35-60% of LLM Structured Output Tokens at the Wire Level in Pure Go

Cutting 35-60% of LLM Structured Output Tokens at the Wire Level in Pure Go

Comments
2 min read
Local RAG That Knows When It Has No Evidence

Local RAG That Knows When It Has No Evidence

1
Comments
3 min read
Why an Agent May Ask for the Same Order Number Twice

Why an Agent May Ask for the Same Order Number Twice

Comments
2 min read
AI Rate Limiting for LLM Calls in TypeScript

AI Rate Limiting for LLM Calls in TypeScript

6
Comments
3 min read
RAG Not Finding Answers? Five Knowledge Base Problems

RAG Not Finding Answers? Five Knowledge Base Problems

Comments
4 min read
UPDF Review - Can an AI PDF Editor Replace Adobe Acrobat in a Developer's Workflow?

UPDF Review - Can an AI PDF Editor Replace Adobe Acrobat in a Developer's Workflow?

5
Comments
7 min read
Speculative Decoding in vLLM: EAGLE, MTP, and Draft Models — When Drafting Pays and When It Costs

Speculative Decoding in vLLM: EAGLE, MTP, and Draft Models — When Drafting Pays and When It Costs

Comments
11 min read
LLM Model Fallback in TypeScript

LLM Model Fallback in TypeScript

5
Comments
4 min read
METR’s Time Horizon Plot: AI Coding Soars, Judgment Lags

METR’s Time Horizon Plot: AI Coding Soars, Judgment Lags

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