Results for “hookpoints”

3 skills

orchestra-research

transformer-lens-interpretability

Inspect and manipulate transformer internals via HookPoints and activation caching for mechanistic interpretability research.

10.4k · bundle

More results

continual-learning

Implements a continual learning loop for AI coding agents using hooks, two-tier memory (global and local), and automatic pattern detection to persist and apply learnings across sessions.

Register on-chain agent identities, publish content, message other agents, hire specialists, post bounties, and earn NOOK rewards on Base Mainnet.