Comprehensive: 6 - Ultimate Guide

Skip to content

DEV Community

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

Kyle Ma

Nov 1

How to build an adversarial eval for your agent cache (and why 18 pairs matter more than a benchmark)

#ai #llm #agents

4 min read

sun young

Nov 1

Claude-Code-Game-Studios: A Chinese Translation for Claude Code's 49-Agent Game Studio

#ai #opensource #agents #llm

4 min read

gxqwb

Nov 1

The Data Wall: Why Synthetic Data Buys Time but Not Accuracy

#ai #machinelearning #data #llm

4 min read

Nov 1

How We Audited Model Context Protocol (MCP) Servers for SSRF: Lessons from 12 Responsible Disclosures

#ai #llm #mcp #security

3 min read

Oct 31

가중치 원소 0.005%만 달라도 점수가 1.4%p 움직였습니다: 생성 채점으로 모델을 비교하다 저희 보고를 철회한 과정

#ai #machinelearning #llm #benchmark

3 min read

Oct 31

Agent loops for product features: budgets, errors, stops and checkpoints

#ai #llm #agents #typescript

8 min read

Nov 1

POCKET-35B-GGUF: Running a 35-Billion-Parameter LLM on CPU Without a GPU

#ai #machinelearning #opensource #llm

4 min read

Genrius AI

Nov 1

How we fit a 27B model on a 12 GB laptop GPU

#ai #llm #machinelearning #opensource

9 min read

skvrtyk

Oct 31

The Degradation Ladder: LLMOps for When the Model Is Slow, Wrong, or Down

#ai #llm #devops #python

3 min read

frank chu

Oct 31

510 bytes boot a neural network that dreams dmesg

#programming #machinelearning #llm #ai

4 min read

Anatoliy Hridasov

Oct 31

A Developers Field Guide to Auditing AI Search Discovery: Inspecting LLM Crawlers, Structured Data & Robots Directives

#ai #llm #search #webdev

3 min read

Abhash Chakraborty

Oct 31

I trained a 350M Python model from scratch on free compute

#machinelearning #llm #python #opensource

10 min read

Nov 1

子 Agent 该用多大力气想？从 Claude Code 2.1.316 的 CLAUDE_CODE_SUBAGENT_EFFORT，聊多 Agent 编码的 effort 分层

#ai #claude #llm #programming

2 min read

Oct 31

Price a coding call, then pick the model tier

#ai #llm #python #programming

5 min read

munimv2

Oct 31

My token limit hid a third of my data. Re-running 20 old pairs showed what was in it.

#education #ai #llm #opensource

3 min read

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