I Benchmarked CodeAct vs Tool Calling. 91% Fewer Tokens.
The CodeAct paper says LLMs should write code instead of calling tools. I tested it with 120 mock API tools on Mistral Small. The token savings are massive.
DevOps Engineer & Full Stack Developer
The CodeAct paper says LLMs should write code instead of calling tools. I tested it with 120 mock API tools on Mistral Small. The token savings are massive.
A practical walkthrough for installing Ollama, setting up Claude Code locally, and getting a zero-cost coding workflow on your laptop.
Master's in Applied Artificial Intelligence
Grenoble, France
Bachelor in Computer Science
Full Scholarship Recipient | Dean's List (Top 10%) | Tomorrow's Leaders Scholar
Semester Abroad
Merit-based exchange scholarship recipient
A static job board for visa-sponsored roles with 30k+ monthly visitors. Built with modern cloud-native technologies.
Published research on feature points extraction methodology for recognizing ancient Egyptian artifacts.
CICD to scrape and send daily list of visa-sponsored jobs to subscribers.