DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Your AI Agent's Memory Is Now an Attack Surface, and Nobody Designed for That

Your AI Agent's Memory Is Now an Attack Surface, and Nobody Designed for That

1
Comments
3 min read
Secure Your TypeScript LLM Pipeline with resk-llm-ts: 11 Threat Detectors in One npm Package

Secure Your TypeScript LLM Pipeline with resk-llm-ts: 11 Threat Detectors in One npm Package

1
Comments
2 min read
Your RAG Pipeline Is Probably Failing Multi-Hop Questions (Here's Why)

Your RAG Pipeline Is Probably Failing Multi-Hop Questions (Here's Why)

Comments 1
3 min read
Kimi K3: Moonshot AI's 2.8-Trillion-Parameter Open Frontier Model — Benchmarks, Architecture, and Everything We Know

Kimi K3: Moonshot AI's 2.8-Trillion-Parameter Open Frontier Model — Benchmarks, Architecture, and Everything We Know

9
Comments
10 min read
🤖 Day 1 - #AIEngineerSeries

🤖 Day 1 - #AIEngineerSeries

1
Comments
1 min read
The cheap open models are out there. Actually using them is the annoying part.

The cheap open models are out there. Actually using them is the annoying part.

Comments
4 min read
Stop Claude Code Token Burn: Constrain CLI Agent Loops with Gradle Test Filters

Stop Claude Code Token Burn: Constrain CLI Agent Loops with Gradle Test Filters

1
Comments
2 min read
I gave my agent the right memory and it ignored it anyway

I gave my agent the right memory and it ignored it anyway

Comments 2
2 min read
Andrej Karpathy Skills review: a single 189k-star CLAUDE.md

Andrej Karpathy Skills review: a single 189k-star CLAUDE.md

1
Comments
5 min read
Fine-Tuning Large Language Models: The Complete 2026 Guide

Fine-Tuning Large Language Models: The Complete 2026 Guide

Comments
2 min read
Have You Outgrown Prompt Engineering?

Have You Outgrown Prompt Engineering?

Comments
3 min read
ChatGPT는 출처를 어떻게 고르나 — 네트워크 트래픽을 읽은 연구, 그리고 2주 만에 절반이 바뀐 이야기

ChatGPT는 출처를 어떻게 고르나 — 네트워크 트래픽을 읽은 연구, 그리고 2주 만에 절반이 바뀐 이야기

Comments
1 min read
OpenKnowledge를 내 지식 볼트에 붙여 볼까 — 겹치는 것, 새로운 것, 그리고 CLA 한 줄

OpenKnowledge를 내 지식 볼트에 붙여 볼까 — 겹치는 것, 새로운 것, 그리고 CLA 한 줄

Comments
1 min read
LLM에게 로봇을 맡겨 봤더니 — Anthropic Embody 벤치마크가 말한 건 로봇 얘기가 아니었다

LLM에게 로봇을 맡겨 봤더니 — Anthropic Embody 벤치마크가 말한 건 로봇 얘기가 아니었다

Comments
1 min read
2026년 7월 16일 AI·LLM 이슈 다이제스트 — 경고는 전부 문서에 적혀 있었다

2026년 7월 16일 AI·LLM 이슈 다이제스트 — 경고는 전부 문서에 적혀 있었다

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