HN Explorer

yohji1984

↗ HN profile [ 42.5 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Why My Open-Source Project Hasn't Done Better

    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 GitHub stars in a very short time. My…

    4 points 3
  2. 1 points 0
  3. Claude Code team should try macro so users can complete 3x as many tasks

    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 — apply patch (edit the testing…

    1 points 2
  4. 1 points 0
  5. Is GPT-5.6 Sol Max Worth It?

    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 difference is not as great as in high mode:…

    2 points 5
  6. Why people chasing after useless token saving plugins and ignoring real solution

    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 to know why people just ignore the…

    2 points 0
  7. Show HN: Agent use 83.1% fewer turns; 16.7 percentage points higher success (turaai.net)
    2 points 0
  8. That is why the tokensaving plugin and skill is completely useless (turaai.net)
    2 points 0
  9. Agent runtime reduces LLM turns by 80% with a higher success rate in DeepSWE (github.com)
    2 points 1