Happy to share that Anthropic fixed a data leakage issue in the iOS app of Claude that I responsibly disclosed. π
π Image URL rendering as avenue to leak data in LLM apps often exists in mobile apps as well -- typically via markdown syntax,
π¨ During a prompt injection attack this was exploitable to leak info.
Recent articles
- Gemini 2.0 Flash: An outstanding multi-modal LLM with a sci-fi streaming mode - 11th December 2024
- ChatGPT Canvas can make API requests now, but it's complicated - 10th December 2024
- I can now run a GPT-4 class model on my laptop - 9th December 2024