2.1K views · 10 likes · 1 reposts (at collection)
Ethan Mollick Says Prompt Injection May Be Less of a Problem in New Models
- Who
- Ethan Mollick
- What
- suggested prompt injection may be less of a problem in new models, consistent with tests showing requests for higher paper grades can no longer be injected
What happened
The inventor of the term "prompt injection" suspects (as do I) that this may not be as large a problem in new models. This matches our tests suggesting that you can't simply prompt inject a request for higher grades in a paper, anymore. https://twitter.com/simonw/status/2113484746999411051
Read next
See the full storyEthan Mollick Suggests Newer Models May Be Less Susceptible to Prompt InjectionThe story so far
Ethan Mollick suggested that prompt injection may be less of a problem in newer models, citing tests that he said suggest a request embedded in a paper can no longer simply induce a model to give it a higher grade. His claim concerns that grading tactic; he presented the broader possibility of reduced susceptibility as a suspicion. Mollick said the person who coined the term “prompt injection” shares that suspicion, linking to a post by Simon Willison.
Keep up with AI, one email a day
Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue · 2026-10-23