I tried Qwen2.5-Coder-7B-Instruct.Q6_K locally with Ollama as the loader, asking it to create a simple Snake game in Python with Pygame and as an extra challenge, the instructions were given in German.

The game works well: the snake grows correctly, the grid and colors are fine. I just had to give the model a little nudge in two places:

- Don’t change the food color every frame
- Avoid recursive gameLoop() for "Play Again"

Qwen2.5 is a great co-pilot that handles most of the work, leaving only minor bugs to correct. German works surprisingly well ("Schlankkörpers" instead of "Schlangenkörper" does not matter, such errors can also occur in large models from time to time...) even though the main language is English. The model supports many programming languages such as: Python, C, C++, Java, JavaScript, HTML/CSS, Bash, SQL… and more.

Conclusion: It still doesn't work completely without programming knowledge, but as a local assistant Qwen2.5-Coder is excellent.

btw my prompt was: "write the game again."

Video workflow:

- Recorded with OBS
- Edited in Kdenlive
- Transcoded with VAAPI (H.264)

No cloud, real hardware.
Everything runs on Linux + Text Generation Web UI (FOSS), so anyone can set this up.
No GPU? No problem, you can also run it using PyTorch’s CPU backend, just much slower.

Background music: ALICE - CROSS THE BORDER (https://www.youtube.com/watch?v=dcqbWgxW4oU)

#Qwen2 #LLM #LocalAI #Ai #vibecoding #Python #Pygame #CodingAI #FOSS #Linux #SnakeGame #Ollama #AIcoPilot #MultilingualAI #TextGenerationWebUI #OBS #Kdenlive #VAAPI #NoCloud #LocalAIWorkflow

#ArtificialIntelligence #PromptEngineering #MultilingualAI
#Localization #AIAlignment #LanguageTechnology #EnterpriseAI

Gemini in Google Sheets doesn’t speak Croatian. It barely speaks British English. Still manually correcting “prioritize” → “prioritise” like it’s 1999. Global AI, local problems. #GoogleSheets #Gemini #AI #Croatian #BritishEnglish #LanguageMatters #MultilingualAI #LLM #FutureOfWork #GoogleAI

A data-driven look at why multilingual LLMs fail at true cross-lingual reasoning, and how culturally intact datasets and new metrics reveal the gap. https://hackernoon.com/multilingual-isnt-cross-lingual-inside-my-benchmark-of-11-llms-on-mid-and-low-resource-languages #multilingualai