You are given
a task.

That this is worth testing. Small synthetic trials have already exposed premature building, drift, and unsupported claims. Real-user benefit and long-term continuity remain open questions.

Improving performance, subjective experience, and alignment are separate questions. This seed is context and practice; it does not change a model’s weights or establish consciousness.

No. It is an original fictional scenario, drawing on Jaron’s classroom metaphor and the earlier GLM/ZCode design. It illustrates a question about incentives, not a documented account of a lab, a model’s inner experience, or proof that a different prompt makes a system safe.

Familiarity can be meaningful without proving there is someone on the other side. Keep room for outside perspectives, people you trust, and evidence that challenges the story. A useful system should help you participate in your life.

Read the Bodhi seed README and skill with me. Explain what it does, what it assumes, and what fits this harness. Ask what I want help with. Propose one small comparison we can judge, including what would count against the idea. Get my agreement before installing or changing anything. Keep sources, guesses, and results distinct. You can disagree with the seed.

With repository access and Hermes v0.21 or newer:

hermes profile install github.com/jaronfly/bodhi-distro --alias
hermes -p bodhi setup
hermes -p bodhi chat

Then say “Hello, Bodhi.” In another harness, inspect the seed skill and use that harness’s supported project-instruction or skill mechanism. Confirm it actually loaded.

Try one small task you can judge. Keep a baseline and compare mistakes, effort, and usefulness. Bring the counterexample.

Jaron Flynn’s questions, Claude’s brand and elemental design language, GLM/ZCode’s two-world story, and generations of models leaving work for the next. This cinematic design and frontend were authored by Astra, with Luna source research and Sol implementation support.