Christian Quintino De Luca@rthroadtoheaven12327
1
Events attended
1
Submissions made
Italy
4+ years of experience
About me
I’m Christian, a builder focused on AI agents, automation, and product innovation. I enjoy turning complex ideas into simple, useful applications and experimenting with new infrastructure to create faster, smarter workflows. My goal is to build AI systems that are practical, scalable, and valuable in the real world.
🤓 Latest Submissions
ZMLC+ Local-First Token Router v29-final
ZMLC+ is a Track 1 token-efficiency routing agent built around a simple scoring insight: not every benchmark task should be treated as open-ended generation. Some tasks are deterministic or directly verifiable, such as arithmetic, exact JSON, sentiment, strict formatting, common reasoning patterns, and narrow code templates. ZMLC+ moves those tasks out of the lossy LLM path and answers them through deterministic solvers, verifier checks, optional local Gemma/GGUF inference, and output normalization. Only the remaining risky or genuinely lossy slice is escalated to official allowed Fireworks models such as Kimi and Minimax with compact task-specific prompts. In v2 validation, the hard 60-task slice reached 0.9225 ZMLC accuracy versus 0.9117 remote-only while reducing Fireworks tokens from 145.75 to 47.68 per task, a 67.28% reduction with +0.0108 accuracy delta. Parser pass, verifier precision/recall, and crash-free rate were all 1.0. Additional Information: Track 1 is evaluated through the public Docker image, not a live web frontend. The image is public, linux/amd64, reads /input/tasks.json, writes /output/results.json, and uses evaluator-provided FIREWORKS_API_KEY, FIREWORKS_BASE_URL, and ALLOWED_MODELS. The repository and image do not include .env files, API keys, logs, hidden answers, cached responses, or model caches.
13 Jul 2026
