DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
An LLM API call, in 4 GIFs

Statelessness and cost-saving tips

An LLM API call, in 4 GIFs

63
Comments 32
4 min read
How Model Distillation Actually Works (and What the 'China Distilled Our Model' Headlines Really Mean)

How Model Distillation Actually Works (and What the 'China Distilled Our Model' Headlines Really Mean)

4
Comments
6 min read
RAG SOTA: I Built SEQUOIA and Tested 7 Pipelines — Full Results

RAG SOTA: I Built SEQUOIA and Tested 7 Pipelines — Full Results

Comments
2 min read
The Open Source Illusion: Why "Free" AI Models Are Getting Expensive

The Open Source Illusion: Why "Free" AI Models Are Getting Expensive

Comments
2 min read
Tracking Five Upstreams, Fuzzing the Parsers, and a Front Door: What Changed in llm-cli-gateway

Tracking Five Upstreams, Fuzzing the Parsers, and a Front Door: What Changed in llm-cli-gateway

1
Comments
8 min read
Fine-Tuning Qwen2.5-0.5B to Write SRE Post-Mortem Summaries

Fine-Tuning Qwen2.5-0.5B to Write SRE Post-Mortem Summaries

1
Comments
4 min read
When You Swap Your AI Agent's Brain — Everything Breaks

When You Swap Your AI Agent's Brain — Everything Breaks

Comments
6 min read
5 walls I hit shipping an AI reading app from West Africa (and what I'd tell past-me)

5 walls I hit shipping an AI reading app from West Africa (and what I'd tell past-me)

Comments
5 min read
MarkItDown: Microsoft's Tool for Converting Almost Anything to Markdown

MarkItDown: Microsoft's Tool for Converting Almost Anything to Markdown

5
Comments 1
4 min read
My Agent Never Said "I Don't Know"

My Agent Never Said "I Don't Know"

Comments
5 min read
Used RTX 3090 Buying Guide for Local LLM in 2026

Used RTX 3090 Buying Guide for Local LLM in 2026

Comments
7 min read
Agentic Web Browsing Workflows with Python and Playwright

Agentic Web Browsing Workflows with Python and Playwright

Comments
7 min read
AI Conf 2026 Moscow: Why I'm Attending (and You Should Too)

AI Conf 2026 Moscow: Why I'm Attending (and You Should Too)

Comments
1 min read
Coverage decay: when style prompts forget themselves

Coverage decay: when style prompts forget themselves

Comments
15 min read
Try the Tech Radar #1 — TOON Cuts JSON Token Cost by 71% for LLM Context

Try the Tech Radar #1 — TOON Cuts JSON Token Cost by 71% for LLM Context

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