‹ BackHN Continuity

Thread

Prompting Claude Opus 5.5

207 points · 227 comments · Michelangelo11

  1. skeledrew · · focus · HN ↗
    All that keeps jumping out at me is how they've set it to refuse giving users thinking tokens and prompts for full reasoning in output. Just drives me further away; I may not stop using Claude completely for now, but I'll be moving even more of my primary workload to Chinese providers. That's where openness and freedom is now at.
    1. wg0 · · focus · HN ↗
      If you're not a noob and you know what you're doing then I can't recommend DeepSeek v4.1 Flash (set to high) enough.
      1. kabes · · focus · HN ↗
        What's special it that noobs shouldn't use it?
        1. kouteiheika · · focus · HN ↗
          In general the weaker the model the more skill you need to drive it (at least if you care about quality).
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.