DEV Community

Open Source

May The Source Be With You! Articles about Open Source and Free Software as a philosophy, and its application to software development and project management.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Introduction to Open-Weights AI Model

Introduction to Open-Weights AI Model

1
Comments
3 min read
RagLeap Core v0.10.1 — I shipped 2 releases in 44 mins after Windows broke everything

RagLeap Core v0.10.1 — I shipped 2 releases in 44 mins after Windows broke everything

Comments
2 min read
Introducing Superfluid: the local-AI native LLM server for multi-agent inference

Introducing Superfluid: the local-AI native LLM server for multi-agent inference

Comments
4 min read
A Practical Guide to Building an Effective QA Testing Strategy

A Practical Guide to Building an Effective QA Testing Strategy

Comments
5 min read
How to Test Whether Agent Memory Keeps Projects Separate

How to Test Whether Agent Memory Keeps Projects Separate

Comments
4 min read
หุ่นเสียง AI ตัวนี้พูดไทยแม่นกว่า ElevenLabs 25 เท่า จริงไหม? แกะ VoxCPM2 สามหมื่นแปดพันดาว

หุ่นเสียง AI ตัวนี้พูดไทยแม่นกว่า ElevenLabs 25 เท่า จริงไหม? แกะ VoxCPM2 สามหมื่นแปดพันดาว

Comments
3 min read
I made the Tiny AI model confused intentionally. Here's how:

I made the Tiny AI model confused intentionally. Here's how:

1
Comments
4 min read
Text and Images in One Embedding Space on a CPU: What I Measured Building a Semantic grep

Text and Images in One Embedding Space on a CPU: What I Measured Building a Semantic grep

Comments 1
10 min read
I Built a $6 Menu Translator Cafes Actually Want (Gemma Local, $0 API Cost)

Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle Submission 💸

I Built a $6 Menu Translator Cafes Actually Want (Gemma Local, $0 API Cost)

Comments 1
3 min read
I Built a Stream to Track Frontier Research in AI vs Cryptography

I Built a Stream to Track Frontier Research in AI vs Cryptography

Comments
2 min read
Nobody conducts the lanterns

Nobody conducts the lanterns

Comments
1 min read
A "decontaminated" dataset still had 52 of HumanEval's 164 problems in it

A "decontaminated" dataset still had 52 of HumanEval's 164 problems in it

Comments 3
3 min read
Your 94% accuracy model might still be a bad model: auditing ML across 7 dimensions

Your 94% accuracy model might still be a bad model: auditing ML across 7 dimensions

1
Comments
4 min read
Stop Pasting Production JWTs and Timestamps into Random Websites: Meet Castov (Web, CLI & VS Code)

Stop Pasting Production JWTs and Timestamps into Random Websites: Meet Castov (Web, CLI & VS Code)

Comments
2 min read
VIDRAFT's VKORE: An NPU Acceleration Software Layer That Unlocks Both Inference *and* Training on Non-GPU Hardware

VIDRAFT's VKORE: An NPU Acceleration Software Layer That Unlocks Both Inference *and* Training on Non-GPU Hardware

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