← @bgSponge

Everything hackable will get hacked

Summary

Malte Ubl argues that AI cyber offense is already here: unsafeguarded open-weight models such as Kimi K3 can map kernel attack surfaces and hunt microVM escapes, even if they failed to break Vercel Sandbox.

  1. The offensive gap is already open.

    Unsafeguarded near-frontier open-weight models such as Kimi K3 already do cyber research at Opus-class strength.

    Kimi K3 is an Opus 4.X-class model with no relevant cybersecurity safeguards.

    As defender, you have the better tool at your disposal, but you have to use it.

  2. A failed sandbox escape is still a research loop.

    Kimi did not leave Vercel Sandbox, but it mapped guest-kernel surface, privilege-escalation paths, and wrote a fuzzer; the right bug would finish the job.

    While none of this produced an escape from Vercel Sandbox, it did show Kimi conducting an investigation on its own

  3. Waiting for Mythos is paralysis.

    Frontier models except Fable 5 already do defensive review; source-code access is the working signal of defensive intent.

    Defenders can already use stronger models than those broadly available for offensive work.

  4. Spend the temporary advantage.

    Sol 5.6 still beats Kimi on defense; run full deepsec reviews now, especially for IDOR, XSS, and SSRF, and keep rerunning as open weights catch up.

  5. Treat AI offense as a budgeted loop.

    Vercel spends tens of thousands on quarterly full reviews plus PR checks, opened Hobby egress firewall, and is redirecting offensive models into a sandbox HackerOne.

Read the original ↗Save to your Sponge

Summarized with Sponge. Quotes are the author’s own words.

More from @bg

All readings →