Post

austin (eeek!/ackkk! 👻)
@thebadcode.com

this is NOT an ai-hater post but i see a lot of folks that reach immediately for tool-using agents to drive the execution of repeatable steps when they could just... have their agent write a script. the latter is likely to be 100x more token-efficient

Arseny Khakhalin@khakhalin.bsky.social

It's fun how I can now achieve the same results by: - writing deterministic code that calls an LLM at some points - writing an LLM skill that calls deterministic code at some points - and everything in between as you develop, the two poles - a harness and a skill - keep expanding until they blend

jfc
@jfc.ninja

during my brief OpenClaw experimentation phase, I managed to burn through all my weekly Claude usage in like three days because I discovered OpenClaw was using the model to filter my to-do list repeatedly instead of having a script do it

No replies yet.