DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
The 4 Levels of AI Agents: Why Most Service AIs Still Feel Dumb (Part 1)

The 4 Levels of AI Agents: Why Most Service AIs Still Feel Dumb (Part 1)

Comments
6 min read
The Multi-Provider LLM Problem: Why “One API” Is Not Enough

The Multi-Provider LLM Problem: Why “One API” Is Not Enough

1
Comments
1 min read
Local LLMs: Bytedance Lance 3B Multimodal, llama.cpp MTP, Ollama Client

Local LLMs: Bytedance Lance 3B Multimodal, llama.cpp MTP, Ollama Client

Comments
3 min read
How Transformers Architecture Powers Modern LLMs

How Transformers Architecture Powers Modern LLMs

Comments
8 min read
Your context window is not your agent's memory

Your context window is not your agent's memory

1
Comments
4 min read
The cheapest model call is the one you don't make

The cheapest model call is the one you don't make

Comments
6 min read
We pre-registered, ran, and verified the macro ablation: information per joule, measured

We pre-registered, ran, and verified the macro ablation: information per joule, measured

Comments
3 min read
I Spent 6 Months Fixing RAG. Here's What I Found (And Built)

I Spent 6 Months Fixing RAG. Here's What I Found (And Built)

1
Comments
5 min read
How to make an AI research agent label facts vs inferences — a deterministic provenance pipeline

How to make an AI research agent label facts vs inferences — a deterministic provenance pipeline

Comments 1
5 min read
I built a fully local AI assistant at 16 — no cloud, no API keys, runs on your GPU

I built a fully local AI assistant at 16 — no cloud, no API keys, runs on your GPU

2
Comments
2 min read
How to Reduce Agent Token Costs From the CLI (2026 Guide)

How to Reduce Agent Token Costs From the CLI (2026 Guide)

Comments
11 min read
О введении триады фильтров для нейросетей и LLM

О введении триады фильтров для нейросетей и LLM

1
Comments
1 min read
AgentThreatBench: The First OWASP Agentic Top 10 Security Benchmark

AgentThreatBench: The First OWASP Agentic Top 10 Security Benchmark

Comments
4 min read
Loading Personality into AI: A Design Philosophy for Separating Memory and Persona

Loading Personality into AI: A Design Philosophy for Separating Memory and Persona

Comments
8 min read
Building Sakhi: Hindi Voice-to-Form for India's ASHA Workers, Solo in Six Weeks

Building Sakhi: Hindi Voice-to-Form for India's ASHA Workers, Solo in Six Weeks

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