# team josh (tollbit.com)

- **Event:** [OpenAI GPT-5 Startup Hackathon](https://cerebralvalley.ai/e/gpt5)
- **When:** Aug 9 at 10:00 AM – Aug 10 at 5:00 PM (PDT)
- **Where:** Location TBA
- **Team:** [Josh Mayer](https://cerebralvalley.ai/u/jash)
- **GitHub:** https://github.com/JoshMayerr/cfg-neuralese
- **Demo video:** https://youtu.be/SDh-NEWipE8
- **Gallery:** https://cerebralvalley.ai/e/gpt5/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/gpt5/hackathon/gallery/9

i set out to find out if a multi agent gpt5 system can learn their own language when optimizing a context free grammar constrained output. tldr: YES!

---

Markdown version of https://cerebralvalley.ai/e/gpt5/hackathon/gallery/9. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt