close

DEV Community

Posts

How We Beat HotSpot Performance (By Cheating, But Not Like That)
Cover image for How We Beat HotSpot Performance (By Cheating, But Not Like That)

How We Beat HotSpot Performance (By Cheating, But Not Like That)

5
Comments
16 min read
Five Gemma-4 models, one accelerator: what porting E2B 31B to AWS Inferentia2 taught me

Five Gemma-4 models, one accelerator: what porting E2B 31B to AWS Inferentia2 taught me

7
Comments
6 min read
Why I built a SQL client when 10 already exist — then let AI agents into it

Why I built a SQL client when 10 already exist — then let AI agents into it

Comments 2
4 min read
Hey DEV, I'm Tobore. Let's actually connect.

Award-winning writer and React Top Author

Hey DEV, I'm Tobore. Let's actually connect.

30
Comments 28
1 min read
Apache Data Lakehouse Weekly: July 11 to July 18, 2026

Apache Data Lakehouse Weekly: July 11 to July 18, 2026

Comments
25 min read
400+ downloads, 0 revenue, and why that's actually fine for now

400+ downloads, 0 revenue, and why that's actually fine for now

10
Comments
2 min read
Your PDFs Are Eating Your LLM's Tokens for Breakfast

Your PDFs Are Eating Your LLM's Tokens for Breakfast

18
Comments 1
5 min read
I built a readability test for my own compression format. It scored 0/24.

Column misalignment in compressed prompts

I built a readability test for my own compression format. It scored 0/24.

2
Comments 4
5 min read
I'm 13, Solo Founder & CEO of Akhouri Systems. No team, no backend, no funding — just a laptop.

I'm 13, Solo Founder & CEO of Akhouri Systems. No team, no backend, no funding — just a laptop.

10
Comments
3 min read
FLUX on a 4070 Graphics Card 🖼️

FLUX on a 4070 Graphics Card 🖼️

6
Comments
4 min read
Porting a 128-expert MoE (Gemma-4 26B-A4B) to AWS Inferentia2 — where every rank weighted the wrong experts

Porting a 128-expert MoE (Gemma-4 26B-A4B) to AWS Inferentia2 — where every rank weighted the wrong experts

2
Comments
6 min read
Anxious About the Tech Market? Try Digging a New Hole

Anxious About the Tech Market? Try Digging a New Hole

Comments
6 min read
My Inferentia port matched its reference token-for-token — and still output garbage

My Inferentia port matched its reference token-for-token — and still output garbage

1
Comments
8 min read
Deterministic Data Engineering With AI Harnesses: Using Claude Code, Codex, Antigravity, and OpenCode for Data Work You Can Actually Trust

Deterministic Data Engineering With AI Harnesses: Using Claude Code, Codex, Antigravity, and OpenCode for Data Work You Can Actually Trust

Comments
19 min read
Your Keycloak roles aren't working in Spring Security. Here's the actual reason.

Your Keycloak roles aren't working in Spring Security. Here's the actual reason.

Comments 1
3 min read
Zero Is Not a Score

Zero Is Not a Score

Comments
4 min read
It Can Die in Its Sleep — Self-Healing launchd Jobs with Multi-Slot Firing and a Done-Marker

It Can Die in Its Sleep — Self-Healing launchd Jobs with Multi-Slot Firing and a Done-Marker

Comments
7 min read
Why Your LLM Pipeline Is Burning 60% of Its Token Budget on Noise (and How to Fix It)

Why Your LLM Pipeline Is Burning 60% of Its Token Budget on Noise (and How to Fix It)

Comments 1
4 min read
loading...