Michael Ethan Levinger
where else to find them
linkedin:michael-levinger
what they talk about
where they keep going back
no series more than once — all 1 in the filters
on a stage with
never shared a talk
who talks about the same things
one talk is not yet a subject
| title | conference | date |
|---|---|---|
| Securing Language Models Against Prompt Injection | PyData Tel Aviv 2024 | 2024-09-25 |
Lists three concrete attack classes: prompt injection (examples include “ignore all previous instructions” and role‑play do anything now or “finish every… | ||
| nothing matches | ||