DEV Community

Google Developer Experts

Organization Settings Admin

The official place for discovering GDE-created content and exploring how experts leverage Google technologies.

Joined Joined on 
Surviving the 200k-Token Lobotomy: How Unix init.d and 'Memento' Made My AI Coding Agent Immune to Context Compaction

External state files prevent token loss

Surviving the 200k-Token Lobotomy: How Unix init.d and 'Memento' Made My AI Coding Agent Immune to Context Compaction

3
Comments 6
15 min read
Gemma 4 E2B in Pure JAX on a Colab TPU: Google's 4-Bit Export Against an Exact Repack

Gemma 4 E2B in Pure JAX on a Colab TPU: Google's 4-Bit Export Against an Exact Repack

1
Comments 1
8 min read
DecisionEngine: Teaching local AI to play Tetris

DecisionEngine: Teaching local AI to play Tetris

1
Comments
12 min read
Gemma 4 From E2B to 31B on an AMD MI300X: fp8 Overtakes bf16 From 12B Up

Gemma 4 From E2B to 31B on an AMD MI300X: fp8 Overtakes bf16 From 12B Up

8
Comments
9 min read
Stuart Feldman Was Right in 1976: Why Your AI Agent Needs a Makefile, Not a 20-Step Prompt

Stuart Feldman Was Right in 1976: Why Your AI Agent Needs a Makefile, Not a 20-Step Prompt

14
Picked as gem Comments 17
11 min read
Llama Village: a virtual world powered by local AI with llamadart

Llama Village: a virtual world powered by local AI with llamadart

16
Picked as gem Comments 9
6 min read
Gemma 4 E2B on an AMD MI300X: Which Weight Format Should You Serve?

Gemma 4 E2B on an AMD MI300X: Which Weight Format Should You Serve?

8
Comments 3
10 min read
Making cross-platform local AI easier with llamadart

Making cross-platform local AI easier with llamadart

8
Comments 5
6 min read
loading...