The letter

One letter a week, in your inbox.

The week's signal, what shipped, what is worth running tonight, and the editor's note. No tracking, no ads, nothing else.

We keep your address, your language and the date you joined, nothing else. Every letter has a one-click unsubscribe link that deletes the record.

← Accept All   Archive
Simon WillisonVoices

Self-generated prompt injections in compaction summaries

September 17

Self-generated prompt injections in compaction summaries In Our framework for reporting model misalignment OpenAI provide "six reports on unexpected or concerning model behavior we’ve observed in the…

aiopenaiprompt-injectiongenerative-ai
Read at Simon Willison ↗

More from Simon Willison on Accept All

More from Simon Willison on Accept All.