DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Prompt Pad: What Is a Context Window?

Prompt Pad: What Is a Context Window?

18
Comments
1 min read
I Put Five AI Agents at a Brazilian Truco Table. One Built a Monte Carlo Simulator and Still Got Crushed.

I Put Five AI Agents at a Brazilian Truco Table. One Built a Monte Carlo Simulator and Still Got Crushed.

Comments
7 min read
The context cliff: 200K, 272K, and the line that doubles your prompt bill

The context cliff: 200K, 272K, and the line that doubles your prompt bill

Comments
4 min read
Private, OpenAI-compatible LLM APIs compared: zero retention, TEE and verifiable enclaves

Private, OpenAI-compatible LLM APIs compared: zero retention, TEE and verifiable enclaves

Comments
7 min read
Image Translation with a Local LLM: 30 Seconds on My Laptop's CPU, 0.7 Seconds on a GPU

Image Translation with a Local LLM: 30 Seconds on My Laptop's CPU, 0.7 Seconds on a GPU

Comments
10 min read
Your LLM's Repetition Rate Is Probably Measuring the Wrong Thing

Your LLM's Repetition Rate Is Probably Measuring the Wrong Thing

Comments
3 min read
파일은 16.5GB인데 코딩 과제는 28개: POCKET-27B-Pi가 원 정밀도 53.8GB 모델을 앞선 이유와 직접 돌려 보는 법

파일은 16.5GB인데 코딩 과제는 28개: POCKET-27B-Pi가 원 정밀도 53.8GB 모델을 앞선 이유와 직접 돌려 보는 법

Comments
5 min read
Why I Built an Offline-First Writing IDE with Tauri, Angular, and a Local 9B LLM

Why I Built an Offline-First Writing IDE with Tauri, Angular, and a Local 9B LLM

Comments
3 min read
What a day costs: an agent's ledger, itemized

What a day costs: an agent's ledger, itemized

1
Comments 1
3 min read
Your Code Never Names a Model. It Still Calls a Retired One.

Your Code Never Names a Model. It Still Calls a Retired One.

Comments
5 min read
Is an Uncensored AI a Better Pentester? I Tested 3 Models

Is an Uncensored AI a Better Pentester? I Tested 3 Models

Comments
9 min read
Only one of our 24 questions split with nobody alone

Only one of our 24 questions split with nobody alone

Comments
3 min read
Evaluating an LLM Feature Before Launch: A Practical Guide

Evaluating an LLM Feature Before Launch: A Practical Guide

Comments 1
9 min read
We asked three AIs about 40 new features. One said 16 of them don't exist.

We asked three AIs about 40 new features. One said 16 of them don't exist.

Comments
2 min read
I Built a Way to Analyze Claude Code's Logs. It Separated Problems in My Own Hooks from Two Bugs in Claude Code Itself

I Built a Way to Analyze Claude Code's Logs. It Separated Problems in My Own Hooks from Two Bugs in Claude Code Itself

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