‹ BackHN Continuity

Thread

Sonnet 5.5

884 points · 613 comments · D2OQZG8l5BI1S06

  1. wongarsu · · focus · HN ↗
    "Sonnet 5.5’s cyber capabilities are a large improvement over Sonnet 5’s, so we’re deploying it with safeguards similar to those on Opus 5.5. Users can still find and fix bugs in their code as part of routine software development, but higher-risk cybersecurity tasks will visibly fall back to Sonnet 5

    Sounds like at least for Anthropic models we reached peak cyber capabilities with Opus 4.8. Everything after that falls back to worse models

    1. gozzoo · · focus · HN ↗
      what is the easyest way to use the chinese models and which harness does work with them well?
      1. Iolaum · · focus · HN ↗
        OpenCode harness with their subscription would be my recommendation.
        1. malshe · · focus · HN ↗
          Between OpenCode and Openrouter which one would you suggest? Sometimes I have pure grunt work to be done on non-sensitive data for which I want to use Chinese models. For example, tasks like extracting something from publicly available large pdf files.
          1. Flere-Imsaho · · focus · HN ↗
            Opencode Go, with the Deepseek 4.1 Flash model feels like a bottomless pit, which is great for grunt work.
            1. malshe · · focus · HN ↗
              OK, I will try it out. Thanks
      2. beveradb · · focus · HN ↗
        opencode with model inference on cheaperinference.com has been working well for me - glm-5.3-flash is shockingly cheap (i've spent a total of a few dollars over several weeks of heavy usage), fast and capable for cyber tasks
      3. asp_hornet · · focus · HN ↗
        Opencode for harness.

        I use GLM directly from z.ai, they do not retain or train on your data accordingly to their TOS.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.