Llm - DEV Community

Skip to content

DEV Community

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

Oct 6

llama.cpp vs Ollama — which one should you run?

#discuss #ai #ollama #llm

5 min read

DHPP

Oct 6

Why Byte-Faithful Pass-Through Beats Protocol Translation for Tool-Calling Agents

#ai #agents #llm #router

4 min read

Oct 6

MCP Connected Your Tools. It Didn't Fix Your Agent's Memory.

#ai #programming #llm #mcp

4 min read

Ward Ed

Oct 6

Benchmark Contamination 101: How Train/Test Overlap Inflates Leaderboard Scores (and How to Catch It)

#machinelearning #llm #benchmark #datascience

7 min read

Oct 6

KV Cache Quantization in LLM Serving: FP8 and INT8 Tradeoffs, the Silent config.json Trap, and How to Measure It Fairly

#llm #vllm #performance #devops

7 min read

jaycodes

Oct 6

Restoring a grant is not restoring capacity

#llm #ai #performance #mlops

9 min read

ai maya

Oct 6

When the attacker is an agent: a defender's field guide to autonomous AI intrusions in 2026

#ai #security #llm #machinelearning

6 min read

Oct 6

OpenAI Started Watermarking ChatGPT Text. Build a Tiny Text Watermark in TypeScript.

#ai #typescript #llm #machinelearning

12 min read

Raihan

Oct 6

Do LLMs Invent Japanese Law Articles? A Bilingual Benchmark

#llm #nlp #japanese #opensource

4 min read

Pratik

Oct 6

How to Build Resilient AI Agents with Search Fallback Loops

#ai #llm #architecture #programming

5 min read

GINIGEN AI

Oct 6

4-bit GGUF Quality for MoE Models: Why Only 3B of 180B Params Fire, and How to Prove Parity

#ai #llm #quantization #edgeai

7 min read

Oct 6

Indirect Prompt Injection Through Tool Descriptions and Tool Output: How Untrusted Metadata Hijacks Agents

#ai #agents #security #llm

7 min read

amrit

Oct 6

Le Chonk Unleashed: Why Mistral’s 1‑Trillion‑Parameter Model Is Shattering LLM Benchmarks

#mistral #llm #openai #ai

5 min read

Nancy Garg for Studio1

Oct 6

Claude Opus 5.5: What Changed, What Breaks, and Whether to Switch

#ai #claude #llm #programming

7 min read

김민식/학생

Oct 6

ZTC (Zero-Token Confidence): juzgar una acción de IA leyendo el estado interno del modelo, con cero tokens extra

#ai #llm #security #spanish

6 min read

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