Skip to content
K = 0.731

Ethan Mollick Suggests Newer Models May Be Less Susceptible to Prompt Injection

1 reports 1 reporting sources 1 hours agoNew

Understand the event

AI overview

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.

Generated by AI from reports · Updated 1 hours ago

Latest development10/23 21:40 (UTC+8)
Ethan Mollick Says Prompt Injection May Be Less of a Problem in New ModelsEthan Mollick · X

Read next

More changes in today’s briefingOlmoEarth v1.3 releases global satellite embeddings and a browser-based mapping explorer

Report timeline

Follow the reports to explore different sides of the event.

10/23
  1. Ethan Mollick · X
    Ethan Mollick Says Prompt Injection May Be Less of a Problem in New Models

    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

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

Event heat trend

There is not enough continuous observation data to plot a trend yet.