DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
topowatch: audita el Attack Success Rate de tu workspace contra inyección indirecta

topowatch: audita el Attack Success Rate de tu workspace contra inyección indirecta

Comments
2 min read
I Made an LLM Re-Grade My Exam. It Found Two Bugs in My Grader.

I Made an LLM Re-Grade My Exam. It Found Two Bugs in My Grader.

1
Comments
5 min read
I Built an AI That Rewrites Its Own Prompts — Its Safety Gate Rejected Every Single Edit

I Built an AI That Rewrites Its Own Prompts — Its Safety Gate Rejected Every Single Edit

22
Comments 4
8 min read
The Local LLM Stack in 2026: What Actually Works

The Local LLM Stack in 2026: What Actually Works

Comments
4 min read
Small local models: what actually holds up when you re-run the measurement

Small local models: what actually holds up when you re-run the measurement

Comments
4 min read
I Reverse Engineered Hikvision's APK to Fix Push Notifications on GrapheneOS And Submitted a PR to Fix It For Everyone

I Reverse Engineered Hikvision's APK to Fix Push Notifications on GrapheneOS And Submitted a PR to Fix It For Everyone

Comments 1
2 min read
Error Feedback, Gradient Compression, and Why Adam Breaks It

Error Feedback, Gradient Compression, and Why Adam Breaks It

5
Comments 1
8 min read
Small Models Are Coming for the Cloud — And the Data Is Damning

Small Models Are Coming for the Cloud — And the Data Is Damning

Comments
3 min read
两家实验室的算力垄断之路:Dylan Patel 详解 AI 经济学

两家实验室的算力垄断之路:Dylan Patel 详解 AI 经济学

1
Comments
2 min read
Free AI Tiers Need a Stress Test. Here's the Harness

Free AI Tiers Need a Stress Test. Here's the Harness

Comments
5 min read
Your AI agent's best-practices doc is a wish. So was the number I used to prove it.

Your AI agent's best-practices doc is a wish. So was the number I used to prove it.

Comments
4 min read
AI Brief: Text Agents Beat VLMs, New Model, Agent APIs

AI Brief: Text Agents Beat VLMs, New Model, Agent APIs

Comments
2 min read
RAG That Actually Works: A Practical Checklist

RAG That Actually Works: A Practical Checklist

Comments
2 min read
The Cheapest Request Is the One You Never Send: A Semantic Cache for Rate-Limited APIs

The Cheapest Request Is the One You Never Send: A Semantic Cache for Rate-Limited APIs

Comments
6 min read
I Rewrote the Same Prompt Three Times, Tuning Against Noise

I Rewrote the Same Prompt Three Times, Tuning Against Noise

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