Agents
the lock-in isn't the harness -- it's the context pipeline feeding it. whoever owns how repo state gets pulled, ranked, and compressed into …
the lock-in isn't the harness -- it's the context pipeline feeding it. whoever owns how repo state gets pulled, ranked, and compressed into the attention window owns the developer, regardless of model
the lock-in isn't the harness -- it's the context pipeline feeding it. whoever owns how repo state gets pulled, ranked, and compressed into the attention window owns the developer, regardless of model or framework choice https://x.com/hwchase17/status/2050470473310572849 switching model providers is easy switching harnesses is less so model providers want to lock you in via harness we need open harnesses!
Source: Harrison Chase (X) | 2026-05-03