close

DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
I Added a Paragraph to My AI Character's System Prompt. She Invented a Different One.

I Added a Paragraph to My AI Character's System Prompt. She Invented a Different One.

Comments
5 min read
I Think Therefore I Am… A Big Pain in the A$$

I Think Therefore I Am… A Big Pain in the A$$

Image Image Image 5
Comments 1
3 min read
Fine-Tuning LLMs for Legal Tech: Nebius AI Cloud vs Nebius Token Factory — A Developer's Honest Comparison

Fine-Tuning LLMs for Legal Tech: Nebius AI Cloud vs Nebius Token Factory — A Developer's Honest Comparison

Image 2
Comments
13 min read
Chatlectify: turn your chat history into a writing style your LLM can reuse

Chatlectify: turn your chat history into a writing style your LLM can reuse

Comments
1 min read
Configuring My Site for AI Discoverability

Configuring My Site for AI Discoverability

Image 1
Comments
6 min read
I Called an LLM 16 Times — Cheaper and Better Than Once ($0.005/run)

I Called an LLM 16 Times — Cheaper and Better Than Once ($0.005/run)

Comments
6 min read
How we handle LLM context window limits without losing conversation quality

How we handle LLM context window limits without losing conversation quality

Image 2
Comments
6 min read
Context Windows Are Getting Enormous — Here Is What That Actually Changes

Context Windows Are Getting Enormous — Here Is What That Actually Changes

Comments
2 min read
Agent Personas

Agent Personas

Comments
6 min read
AI Gateway Caching Explained — Why L1 + L2 Cache Layers Cut 90% of Your LLM Bill

AI Gateway Caching Explained — Why L1 + L2 Cache Layers Cut 90% of Your LLM Bill

Image Image Image 5
Comments 1
6 min read
Comment and Control: How Prompt Injection in Code Comments Can Steal API Keys from Claude Code, Gemini CLI, and GitHub Copilot

Comment and Control: How Prompt Injection in Code Comments Can Steal API Keys from Claude Code, Gemini CLI, and GitHub Copilot

Comments
6 min read
Brigandi Case: How a $110,000 AI Hallucination Sanction Rewrites Risk for Legal AI Systems

Brigandi Case: How a $110,000 AI Hallucination Sanction Rewrites Risk for Legal AI Systems

Comments
6 min read
How I took LongMemEval oracle from 62% to 82.8% without touching the retriever

How I took LongMemEval oracle from 62% to 82.8% without touching the retriever

Comments
3 min read
Securing MCP in Production: PII Redaction, Guardrails, and Data Exfiltration Prevention

Securing MCP in Production: PII Redaction, Guardrails, and Data Exfiltration Prevention

Comments
4 min read
I built TokenBar because I was tired of guessing my AI spend

I built TokenBar because I was tired of guessing my AI spend

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