‹ BackHN Continuity

Thread

DeepSeek v4.1 Flash Is Now Our Best Hacking Model

177 points · 67 comments · talhof8

  1. TuxSH · · focus · HN ↗
    I find this - or perhaps the title - a bit surprising.

    I've benchmarked GLM 5.3 and DSv4.1-F on my fully-annotated decomp of the Nintendo 3DS's kernel, which I have a good mental understanding of, tasking them to find vulns and other bugs (in Max mode w/ subagents). GLM 5.3 founds almost all the vulns in 30min for $22, while DS only found one vuln for $2 in 40min.

    Perhaps DS works better where targets have low-hanging fruits than can be found fast?

    1. allie1 · · focus · HN ↗
      I think it really depends on what the data DS was fine tuned on. If your use case is very specific, it wouldn’t have distilled that knowledge well.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.