Viewing profile — yohji1984

Since the beginning of 2026, many projects such as RTK, Caveman, and Ponytail have claimed that they can reduce token usage by 80–90%. Some of them gained tens of thousands of GitH…

[flagged]

Sorry I will edit the post

So the idea is really simple. If CC need to change a file and run some test, CC needs to: # Turn 1 — apply patch (change package file) # Turn 2 — apply patch (fix the bug) # Turn 3…

I ran some test with gpt- 5.6 sol in max reasoning on both codex cli and my own agent harness: https://github.com/Tura-AI/tura I tested only 1 task and the toekn efficency differen…

I wrote a blog yesterday on how useless RTK and Ponytail are on real coding tasks. And published my agent harness long-horizon task benchmarks on 80% real token saving. I just want…

Hi HN, I've been working on an agentic runtime framework. The earlier benchmark eval is promising. But I can see the limits of the test design and the fragility of the runtime itse…

Sorry, I missed the Open Items section. You're right about that, designing a good eval harness can be difficult and expensive. Maybe we need some kind of community project for agen…

I'm wondering why all these token-saving solutions focus their benchmarks exclusively on simple Q&A tasks. If their tools truly saved money in real, long-term programming tasks, th…