Re:Clean up Claude 5's token vomit with a separate LLM
by zachahn on Thursday August 20, 2026 @01:46PM
(#49377806)
I totally agree that hooks help to shovel our instructions through to Claude, but it's so dumb we have to waste tons of tokens (repeated verbatim, over and over) (that we pay for), just to have it ignore the instructions anyway.
I wrote a little bit about it on my blog post. It's a waste of money and compute.
Re:Clean up Claude 5's token vomit with a separate LLM
by sulZ on Thursday August 20, 2026 @01:17PM
(#49377453)
I’d be interested in seeing and using this harness if you’re willing to share
Re:Clean up Claude 5's token vomit with a separate LLM
by unglaublich on Friday August 21, 2026 @07:47AM
(#49386697)
That's what system reminders do in most harnesses. https://michaellivs.com/blog/system-reminders-steering-agent...
This is because these harnesses are missing a very important feature. Anything like this needs to be included with every turn, otherwise the LLM quickly drifts.
I first noticed it when I wrote a harness for D&D (because it's so damn noticeable there), but now I include this for any harness I write.