Our readingWhat is a korrent?
Drawn from what Zvi Mowshowitz said
prompt injection Getting an agent to follow instructions it found instead of the ones it was given.
It is in practice safe to assume your agents are not going to get prompt injected, even if you are kind of asking for it.
Added to korrents 4 Sept 2026 · How quotes work · Something wrong? Tell us
Do you hold this korrent?Do you also believe this?
I hold this tooCannot both be true
Auto-mode does not yet convincingly fix prompt-injection risk for coding agents.
Both men are looking at the same defence — auto mode — one month apart, and answering the same practical question opposite ways. Mowshowitz says it is in practice safe to assume your agents will not get prompt injected even if you are asking for it; Willison says he really wants to believe it fixes prompt injection for coding agents and is just not there yet. Someone deciding whether to point an agent at untrusted input cannot follow both.
In tension with
Steinberger and Mowshowitz agree the models got much harder to inject and disagree about what follows from that. Steinberger keeps the problem open — unsolved, merely harder — while Mowshowitz converts the improvement into an operating assumption. The gap between "harder" and "safe to assume" is exactly where the remaining risk lives.
Shared subject first, then similar wording. They may agree or disagree.