HN Explorer

skysniper

↗ HN profile [ 50.2 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: Inter-session messaging between Claude Code sessions (github.com)

    I typically run multiple Claude Code sessions at the same time. Sometimes I need my existing sessions to work together, but CC does not support inter-session messaging so I have to be the message bus. I was tired of…

    1 points 0
  2. Opus 4.7 dominates agentic benchmark, 15% more expensive than Opus 4.6 (app.uniclaw.ai)
    3 points 1
  3. GLM-5.1 matches Opus 4.6 in agentic performance, at ~1/3 actual cost (app.uniclaw.ai)
    22 points 1
  4. StepFun 3.5 Flash is #1 cost-effective model for OpenClaw tasks (300 battles) (app.uniclaw.ai)
    175 points 22
  5. Show HN: OpenClaw Arena – Benchmark models on real tasks, rank by perf and cost (app.uniclaw.ai)

    We built an arena for comparing AI models on real agentic tasks — not chat or static benchmarks. Models run as actual OpenClaw subagent in fresh VMs with full tool access, and results feed into two separate…

    2 points 0