yoavshmariahu

yoavshmariahu on Hacker News

Re:Show HN: Thinker – Trim context and cache knowledge to extend agent... on Thursday November 05, 2026 @05:48PM (#50385622)

Right now the cost estimator assumes payoff needs to be met by 20 calls but its very conservative so it typically beats that. There are cases where we cut context and then it needs to be re-read e.g. https://thinker.sh/see-the-data?run=click-1. In this example it stays cost-effective since the re-read is small, but we're continuing to experiment with how long we wait before we consider context to be safe to remove.

Show HN: Thinker – Trim context and cache knowledge to extend agent usage limits

Posted by yoavshmariahu on Thursday November 05, 2026 @02:22PM
from the show-hn dept.

https://thinker.sh/how-it-works

I’ve been doing a lot of solo development lately and found myself hitting Claude token limits halfway through the week constantly. Even with a Max plan, I’d have to switch over to Codex or Cursor, and it would be a bit difficult to get used to the nuances of each harness.It’s still a problem for me, but I finally built Thinker to save me some tokens and help me get a bit more out of my coding...

( Read More... | 2 comments | on HN )