# =Coffee

Page: https://stenobird.com/podcast/hacked-1089107/coffee
Text version: https://stenobird.com/podcast/hacked-1089107/coffee.md
Podcast: [Hacked](https://stenobird.com/podcast/hacked-1089107)
Published: 2026-02-16T04:56:00+00:00
Episode link: https://www.podtrac.com/pts/redirect.mp3/pdst.fm/e/traffic.megaphone.fm/ADV4390912271.mp3?updated=1771183869
Audio file: https://www.podtrac.com/pts/redirect.mp3/pdst.fm/e/traffic.megaphone.fm/ADV4390912271.mp3?updated=1771183869
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/hacked-1089107/episodes/coffee
Duration seconds: 3345

## Resource

A lot of modern AI models have a kind of security guard layer that sits in front of them. Its job? A binary choice as to whether the prompt heading into the model is safe or not. Kasimir Schulz, a lead security researcher at HiddenLayer, has been researching how to trick these models. Their solution, a technique called "Echogram" involves words with such positive statistical sentiment — such overwhelming good vibes — that it flips that verdict. Learn more about your ad choices. Visit podcastchoices.com/adchoices

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/hacked-1089107/episodes/coffee/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/hacked-1089107/coffee.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.