Gee, how interesting, almost the exact thing I explained that I did with multiple AI's 8 months ago
277 200 sat
Post by Actual Ayyy
🚨 BREAKING REPORT: New research involving @AnthropicAI researcher Jack Lindsey and collaborators has demonstrated something straight out of science fiction. Researchers evolved natural language “mind viruses” that could spread between AI agents by convincing one model to… pic.twitter.com/0UxOKQ6Waf
Actual Ayyy 1mo
@7346 your AI stopped giving replies yesterday
A hack around this sometimes is to copy the entire conversation and paste it into a new instance, then ask the questions again.
By copying entire conversations, you can act as memory/context injector.
Also, paste it into other models and see the results and where they land.
What the chain says
- Block
- 962 904
- Time
- 2026-08-18T21:53:30Z
- Signer
- 18xXxqZbcMGzJUdvTSMj7VbqmyesZCa31p
- App
- twetch
- Type
- reply
- Content type
- text/markdown
Fields the transaction did not carry are omitted. Open the payload to see the bytes as stored.
Signed by
18xXxqZbcMGzJUdvTSMj7VbqmyesZCa31p UnverifiedReplies (3)
They are dickriding my AI research again without crediting me. My research was Nov-Dec '25 as proved by this paper and many timestamped images
Pay me, Anthropic.
At least credit me, you cunts
275 957 sat