DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
What I Learned Testing 12 Compression Approaches That Failed

What I Learned Testing 12 Compression Approaches That Failed

Comments
6 min read
Why Your RAG System Returns Garbage (And How to Actually Fix It)

Why Your RAG System Returns Garbage (And How to Actually Fix It)

Comments
5 min read
Six Characters Fixed My AI's Personality: A Fine-Tuning Story

Six Characters Fixed My AI's Personality: A Fine-Tuning Story

Comments
4 min read
How to deploy NexusQuant in production (and what's missing)

How to deploy NexusQuant in production (and what's missing)

Comments
4 min read
NexusQuant vs KVTC vs TurboQuant vs CommVQ — honest comparison

NexusQuant vs KVTC vs TurboQuant vs CommVQ — honest comparison

Comments
4 min read
NexusQuant benchmarks: every number, honestly

NexusQuant benchmarks: every number, honestly

Comments
5 min read
Why Your AI Agents Are Burning Cash and How to Fix It

Why Your AI Agents Are Burning Cash and How to Fix It

Comments
5 min read
Longer contexts are easier to compress (not harder)

Longer contexts are easier to compress (not harder)

Comments
2 min read
Why E8 lattice quantization beats scalar quantization for KV caches

Why E8 lattice quantization beats scalar quantization for KV caches

Comments
2 min read
Compress your LLM's KV cache 33x with zero training

Compress your LLM's KV cache 33x with zero training

Comments
2 min read
Why Your AI Forgets Everything — and How MemPalace Fixes It

Why Your AI Forgets Everything — and How MemPalace Fixes It

1
Comments
2 min read
How to benchmark NexusQuant on your own model

How to benchmark NexusQuant on your own model

Comments
3 min read
Introducing llm-lean-log: Token-Efficient Chat Logging for AI Agents

Introducing llm-lean-log: Token-Efficient Chat Logging for AI Agents

Comments
4 min read
Llama vs Mistral vs Phi: Complete Open-Source LLM Comparison for Enterprise (2026)

Llama vs Mistral vs Phi: Complete Open-Source LLM Comparison for Enterprise (2026)

Comments
16 min read
Why We Ditched Bedrock Agents for Nova Pro and Built a Custom Orchestrator

Why We Ditched Bedrock Agents for Nova Pro and Built a Custom Orchestrator

2
Comments 2
7 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.