That's an interesting model. It sounds closer to a private club than a traditional social network, where trust is negotiated by the community rather than just the administrator.
HN user
roshiya
Building Anchor, a local tool for restoring cognitive continuity after interruptions.
Do you see OpenAI compatibility mainly as a migration path, or do you expect it to become the de facto interface for local model tooling as well?
Interesting assumption about a future with frontier-level open-weight models. Do you see Wolffish primarily as an agent framework, or as a "personal operating system" for AI workflows?
Curious why you chose invite-only access. Was the goal primarily spam prevention, community building, or reducing moderation requirements?
Out of curiosity, how many generated boards get rejected before finding a guess-free puzzle at the higher difficulty levels? The 3,000-attempt limit caught my attention.
Curious which part ended up being the hardest to fit into PICO-8's limits code size, art, or music?