DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Deterministic AI

Deterministic AI

Comments 1
2 min read
What 11 big tech companies actually do with AI in 2026

What 11 big tech companies actually do with AI in 2026

Comments
23 min read
tierKV: A Distributed KV Cache That Makes Evicted Blocks Faster to Restore Than GPU Cache Hits

tierKV: A Distributed KV Cache That Makes Evicted Blocks Faster to Restore Than GPU Cache Hits

1
Comments
3 min read
How a $0.02/Call Model Scored 78.2% on SWE-bench Verified — Beating Every Model on the Leaderboard

How a $0.02/Call Model Scored 78.2% on SWE-bench Verified — Beating Every Model on the Leaderboard

Comments
7 min read
Stop Guessing Your RAG Quality: Automating Faithfulness Metrics with Spring AI and LLM-as-a-Judge

Stop Guessing Your RAG Quality: Automating Faithfulness Metrics with Spring AI and LLM-as-a-Judge

Comments
2 min read
Open-WebUI + Ollama Guide: Run LLMs Locally with Docker

Open-WebUI + Ollama Guide: Run LLMs Locally with Docker

Comments
4 min read
How I Built a Red/Blue Team Loop That Teaches My AI Firewall to Defend Itself

How I Built a Red/Blue Team Loop That Teaches My AI Firewall to Defend Itself

Comments
8 min read
Your Cron Jobs Can't Think. These Can.

Your Cron Jobs Can't Think. These Can.

Comments
6 min read
What I Learned Building a Lightweight Local AI Agent

What I Learned Building a Lightweight Local AI Agent

1
Comments
9 min read
One Open Source Project a Day (No. 60): OpenHarness - Lightweight AI Agent Infrastructure Framework

One Open Source Project a Day (No. 60): OpenHarness - Lightweight AI Agent Infrastructure Framework

Comments
8 min read
Anthropic prompt caching cut our RCA cost by 90%

Anthropic prompt caching cut our RCA cost by 90%

Comments
7 min read
You're doing RAG wrong

You're doing RAG wrong

1
Comments
6 min read
How a Morse Code Attack Bypassed Bankr's LLM Agent: T1027 Obfuscation in the Wild

How a Morse Code Attack Bypassed Bankr's LLM Agent: T1027 Obfuscation in the Wild

Comments
11 min read
Prompt injection through website content: how AI agents can be manipulated by the pages they visit

Prompt injection through website content: how AI agents can be manipulated by the pages they visit

Comments
4 min read
Local AI Updates: llama.cpp MTP, vLLM Gemma 4 Speeds, Ollama Coder Benchmarks

Local AI Updates: llama.cpp MTP, vLLM Gemma 4 Speeds, Ollama Coder Benchmarks

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