After 7 Months, Glasswing Overwelms Maintainers with Underwhelming Findings

Re:After 7 Months, Glasswing Overwelms Maintainers with Unde... by lifeisloving on Tuesday November 10, 2026 @09:47PM (#50449208)

I have these things running 24/7 working on apks. They are extermely underwhelming, I spend most mornings annoyed looking at hallucinated/incomplete/insignificant findings from overnight.

Im about ready to stop using them overnight in this autonomous fashion. Its a great "intelligent" fuzzer but pretty mediocre when its steering the ship by itself.

[ Parent | on HN ]

Re:After 7 Months, Glasswing Overwelms Maintainers with Unde... by cheesecompiler on Tuesday November 10, 2026 @10:51PM (#50449567)

can you elaborate?

[ Parent | on HN ]

Re:After 7 Months, Glasswing Overwelms Maintainers with Unde... by lifeisloving on Wednesday November 11, 2026 @06:18PM (#50460359)

Im not sure why I got downvoted here. Anybody that does this everyday knows you cannot just find exploits with llms without holding their hand and steering them in the right direction.

I cannot say what exactly I work on, but with llms its typical static&dynamic analysis on apks. And they really wouldn't have any sucess without my verbose skills, direction and tooling. They cannot operate by themselves and surface anything significant, atleast not in my experience.

[ Parent | on HN ]