DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Fixing blind spots in code reviews with Hindsight memory

Fixing blind spots in code reviews with Hindsight memory

Comments
2 min read
Best AI Agent Security & Guardrails Tools in 2026: LLM Guard vs NeMo vs Guardrails AI

Best AI Agent Security & Guardrails Tools in 2026: LLM Guard vs NeMo vs Guardrails AI

Comments 1
3 min read
MCP Tool Poisoning: The AI Supply Chain Attack Nobody Is Talking About

MCP Tool Poisoning: The AI Supply Chain Attack Nobody Is Talking About

Comments 2
4 min read
Agent Series (2): ReAct — The Most Important Agent Reasoning Paradigm

Agent Series (2): ReAct — The Most Important Agent Reasoning Paradigm

Comments
11 min read
Five habits that separate the operator from the vibe-coder

Five habits that separate the operator from the vibe-coder

Comments
6 min read
Semantic caching thresholds and why they matter

Semantic caching thresholds and why they matter

Comments
12 min read
Gate Zero: stop unfalsifiable prompts before they canonicalize as specs

Gate Zero: stop unfalsifiable prompts before they canonicalize as specs

Comments
5 min read
Eval-driven development for a local-LLM agent: how I shipped Lore 0.2.0 with confidence

Eval-driven development for a local-LLM agent: how I shipped Lore 0.2.0 with confidence

1
Comments
6 min read
Your Claude Code rules are a liability you'll never audit

Your Claude Code rules are a liability you'll never audit

Comments
6 min read
Qwen 3.6 Ollama Release, Consumer GPU Benchmarks, GGUF Quantization Fixes

Qwen 3.6 Ollama Release, Consumer GPU Benchmarks, GGUF Quantization Fixes

Comments
4 min read
The Speculative Decoding Pattern

The Speculative Decoding Pattern

2
Comments 2
3 min read
I Stacked 4 More Context Layers on Top of RAG. Sonnet Got 12% Better. Haiku Got 14% Worse.

I Stacked 4 More Context Layers on Top of RAG. Sonnet Got 12% Better. Haiku Got 14% Worse.

Comments 2
5 min read
Traditional Quantization vs 1.58-Bit Ternary Models: A Practical Comparison

Traditional Quantization vs 1.58-Bit Ternary Models: A Practical Comparison

Comments 1
5 min read
luckrig: a concept for tasting LLM rigs, not just models

luckrig: a concept for tasting LLM rigs, not just models

Comments 1
2 min read
How to structure JSON for LLMs (and stop wasting tokens)

How to structure JSON for LLMs (and stop wasting tokens)

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