# Method

- **Event:** [GPT-6 Astra Hackathon NYC](https://cerebralvalley.ai/e/openai-gpt-6-astra-nyc)
- **When:** Thu, Sep 10 at 9:00 AM – 10:00 PM (EDT)
- **Where:** New York, NY
- **Placement:** 3rd Place
- **Team:** [Ryan Prendergast](https://cerebralvalley.ai/u/ryanp)
- **GitHub:** https://github.com/method-ai-hq/method-factorio
- **Demo video:** https://youtu.be/NSV9bYdfrEo
- **Gallery:** https://cerebralvalley.ai/e/openai-gpt-6-astra-nyc/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/openai-gpt-6-astra-nyc/hackathon/gallery/21

Using Astra to beat Astra. Continuous policy search for long-horizon tasks. I used Astra to design a strategy to play factory that runs faster and more accurately on repeated iterations than just prompting Astra.

 View results here https://method-ai-hq.github.io/method-factorio/

My goal is to use this to make vertical ai (AI for X) faster and more accurate, especially in tough to verify domains. that's what my startup is doing (hill climbing in hard to verify domains, withmethod.ai).

---

Markdown version of https://cerebralvalley.ai/e/openai-gpt-6-astra-nyc/hackathon/gallery/21. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt