Which AI Wrote It? A Blind Test Game Using Netlify AI Gateway
Event description:
A new frontier model drops almost every week now.
Claude Opus 5.5 and Sonnet 5.5 landed in the last few weeks, OpenAI shipped GPT-6.1 Sol, and Mistral Large 4 just arrived as the newest open model. Everyone has a favorite, but which one actually writes better for the work you do? On Thursday, KP and Tania are going to find out, blind.
We'll give the models real tasks from two jobs: community and social media. Tania will pick hers from a menu of community asks, and you'll pick the social ones from the chat. Every model gets the same prompt through Netlify AI Gateway, the outputs go up as A, B, C, and D, and everyone picks a favorite before we reveal who wrote what.
The real star is the swap. One app, one setup, and a drawer full of models from every major lab. Don't like the lineup? We'll pull a different model and rerun the task in seconds, live, with no new API keys and no redeploy.
This one is for people who know their field cold and don't write code. If you've ever wondered whether the famous model is worth it for your work, come and judge along with us.
Thursday, October 8, 12:00 PM ET. Bring a task you'd want the models to fight over.
Agenda
0:00 Why model choice got hard: a new frontier release every week
0:05 The setup: one app, every model, all through Netlify AI Gateway
0:10 Round one: Tania picks a community task, blind test, then the reveal
0:25 Round two: the audience picks a social media task, votes blind, then the reveal
0:40 Swap it live: pull new models from the drawer and rerun the tasks
0:50 What we learned about picking models, plus your questions
Key Links:
→ Join our Discord
→ Sign up to Netlify