All
Articles 131,777Blog Posts 136,637Tech Tutorials 34,158Research Papers 25,924News 18,712
⚡ AI Lessons
Dev.to · xbill
6h ago
Teaching Codex to Paint: A Stateful Image-Editing Skill Built on Gemini's Interactions API and MCP
How nb2lite-skill-codex packages Google's gemini-3.1-flash-lite-image as a Codex skill + MCP server — with Codex-native install paths, stateful edits, and a dog
Dev.to · xbill
13h ago
Teaching Claude Code to Direct: A Stateful Video-Editing Skill Built on Gemini's Interactions API and MCP
How omni-skill-claude packages Google's gemini-omni-flash-preview as a Claude Code skill + MCP server — what Omni Flash actually does, a field guide to all eigh
Dev.to · xbill
1d ago
Teaching Claude Code to Paint: A Stateful Image-Editing Skill Built on Gemini's Interactions API and MCP
How nb2lite-skill-claude packages Google's gemini-3.1-flash-lite-image as a Claude Code skill + MCP server — with multi-turn stateful edits, an idiot-proof inst
Dev.to · xbill
3d ago
Gemma 4 E2B on a Single TPU v6e Chip: A Serving Deep Dive
What it took to deploy, why the QAT checkpoints refuse to load, and what one flex-start v6e chip is actually worth — measured live.
Dev.to · xbill
3d ago
Gemma4 DevOps In Action
In the last entry I got Gemma-4's 128-expert MoE running on an inf2.24xlarge and signed off with...
Dev.to · xbill
3d ago
Inferntia2 DevOps in Action
In the last entry I got Gemma-4's 128-expert MoE running on an inf2.24xlarge and signed off with...
Dev.to · xbill
6d ago
Five Gemma-4 models, one accelerator: what porting E2B 31B to AWS Inferentia2 taught me
I ported the whole Gemma-4 family — E2B, E4B, 12B, 31B, and the 26B-A4B MoE — to run on...
Dev.to · xbill
6d ago
Porting Gemma-4 12B (the encoder-free multimodal one) to AWS Inferentia2
The 12B ships as a multimodal class with no encoder loaded, and its sliding-window attention overflows Neuron's fused-attention SBUF. Three surgical fixes and i
Dev.to · xbill
6d ago
My Inferentia port matched its reference token-for-token — and still output garbage
Porting Gemma-4 31B (dense) to AWS Inferentia2: the tensor-parallel recipe that worked at 12B collapses at 31B, NxD ModelBuilder saves it — and then a passing v
Dev.to · xbill
6d ago
Porting a 128-expert MoE (Gemma-4 26B-A4B) to AWS Inferentia2 — where every rank weighted the wrong experts
The MoE was the hard one: a dual-path FFN, a sparse expert loop that won't trace, and a bug where the device output was empty while the CPU reference was perfec
Dev.to · xbill
6d ago
Five Gemma-4 models, one accelerator: what porting E2B 31B to AWS Inferentia2 taught me
A side-by-side of all five Gemma-4 variants on Inferentia2 — PLE, KV-sharing, MatFormer, mixed attention, and a 128-expert MoE — the recipe that evolved to carr
Dev.to · xbill
1w ago
Smash Story: The Demo Script That Out-Debugged My Test Suite
A green 10-test suite, a broken production default, and the 10-minute smash — how a live demo caught an API-contract bug that mocks never could.
Dev.to · xbill
1w ago
My Demo Script Found a Production Bug on Its First Run: A Tiny Post-Mortem
How a narrated demo for an MCP image server caught an API-contract drift that 10 passing unit tests never could — root cause, fix, and lessons about mocked test
Dev.to · xbill
1w ago
Build One AI Tool Server, Call It From Three Different Agents (MCP Explained)
A beginner-friendly tour of the Model Context Protocol: one Python server that generates images with Gemini, called by Claude Code, a Google ADK agent, and a Ru
Dev.to · xbill
⚡ AI Lesson
1w ago
Why did my benchmark stop at N=22? A debugging story in nine bugs
Submission for DEV's Summer Bug Smash — Smash Stories track. There was a file in my repo called...
Dev.to · xbill
⚡ AI Lesson
1w ago
My benchmark's Python column was N/A for a year — CPython's 4300-digit limit, and eight other bugs
Submission for DEV's Summer Bug Smash — Clear the Lineup track. The...
Dev.to · xbill
1w ago
TPU Deployments with Gemma 31B, v6e-8, and Antigravity CLI
This article provides a step by step debugging guide for deploying Gemma 4 to a Google Cloud TPU...
Dev.to · xbill
1w ago
Porting Gemma-4 (2B / 4B / 12B) to AWS Inferentia2
A field report on running Google's Gemma-4 on AWS Inferentia2: mixed attention heads, the vLLM / optimum-neuron / NxD dead-ends, and the neuronx-cc compiler lim
Dev.to · xbill
1w ago
Porting Gemma-4 (2B / 4B / 12B) to AWS Inferentia2
A field report on running Google's Gemma-4 on AWS Inferentia2: mixed attention heads, the vLLM / optimum-neuron / NxD dead-ends, and the neuronx-cc compiler lim
Dev.to · xbill
1w ago
GRIND404: I turned my "Passion" for LeetCode into a playable arcade game
This is a submission for the DEV Weekend Challenge: Passion Edition. What I Built My...
Dev.to · xbill
2w ago
Debugging Deployments with Gemma 4B, TPU v6e-1, MCP, and Antigravity CLI
This article provides a step by step debugging guide for deploying Gemma 4 to a Google Cloud TPU...
Dev.to · xbill
☁️ DevOps & Cloud
⚡ AI Lesson
2w ago
Debugging Deployments with Gemma 4B, TPU v6e-4, MCP, and Antigravity CLI
This article provides a step by step debugging guide for deploying Gemma 4 to a Google Cloud TPU...
Dev.to · xbill
🧠 Large Language Models
⚡ AI Lesson
2w ago
MCP Configuration for Looker with Antigravity CLI
This article covers the MCP setup and configuration for using Looker and underlying Gemini LLM with...
Dev.to · xbill
☁️ DevOps & Cloud
⚡ AI Lesson
2w ago
Omni Flash Preview with Claude Code
This article covers the MCP setup and configuration for using Google Omni Preview and underlying...
DeepCamp AI