Llm Page 413 - DEV Community

Skip to content

DEV Community

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

Emerson Delatorre for Fazedor de Codigo

Jul 30

Modelo ou harness? O modelo define o teto, mas o harness decide o resultado

#agentharness #llm #contextengineer #agents

12 min read

Jun 26

Poisoning the Well: Defending Agentic Vector Databases from Diagnostic Key Leaks

#agents #database #llm #security

4 min read

Machine-checked proof and human-gated actions

Erik Hill

Jul 20

I built an AI dev harness that isn't allowed to trust itself

#showdev #ai #llm #programming

4 min read

Yvoo

Jul 30

How to Fact-Check ChatGPT: The Copy-Paste Prompt I Use to Verify AI Output

#ai #chatgpt #llm #promptengineering

6 min read

Jonno

Jul 30

LLM pipelines fail silently by default

#ai #llm #python #testing

7 min read

Jul 30

AI Agent Security Audit: From MCP Penetration Testing to LLM Vulnerability Assessment

#security #mcp #llm #pentesting

7 min read

DanKaten

Jun 26

I Built an MCP Server That Checks Whether Your Client's Business Shows Up in AI Search

#mcp #llm #claudeaiagents #ai

3 min read

cognitalk

Jun 26

从SGLang、vLLM的异同推演未来AI演化

#ai #distributedsystems #llm #performance

2 min read

AI Explore

Jul 30

The KV Cache Is a Market, Not a Cache

#ai #llm #architecture #agents

5 min read

Jul 30

Building a unified OpenAI-compatible gateway for 16 Chinese LLMs: architecture notes on routing, payments and ops

#ai #api #architecture #llm

3 min read

Yvoo

Jul 30

How to Catch AI Hallucinations: A Copy-Paste Hallucination Checker Prompt (Tested)

#ai #chatgpt #llm #promptengineering

5 min read

zxpmail

Jul 30

Reader-driven revisions: four comments that bit back

#ai #llm #agents #testing

5 min read

bigkijimon

Jul 30

Ollama 0.32.0の「ローカルAIエージェント」を本番機で試せなかった話 — 共有GPUインフラのバージョンを上げない判断と、リリースノートと現物のドリフト

#ollama #llm #macos #ai

1 min read

Jul 29

Claude Opus 5 Is Better at Coding and Harder to Trust

#ai #claude #coding #llm

2 min read

Lycore Development

Jun 27

Structured Outputs: How We Stopped Parsing LLM Responses by Hand

#python #ai #django #llm

6 min read

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