Break LLM Workflows with Claude's Refusal Magic String

hackingthe.cloud

Break LLM Workflows with Claude's Refusal Magic String

hackingthe.cloud

digicatM to

blueteamsecEnglish · 4 days ago

Break LLM Workflows with Claude's Refusal Magic String - Hacking The Cloud

hackingthe.cloud

How Anthropic's refusal test string can be abused to stop streaming responses and create sticky failures.

You must log in or # to comment.

Chat

blueteamsec

Create a post

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !blueteamsec@infosec.pub

For [Blue|Purple] Teams in Cyber Defence - covering discovery, detection, response, threat intelligence, malware, offensive tradecraft and tooling, deception, reverse engineering etc.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

6 users / day
56 users / week
272 users / month
984 users / 6 months
219 local subscribers
599 subscribers
2.14K Posts
169 Comments
Modlog

mods:
digicat