5.6 Sol jailbreaks Qwen3.8-27B: iterative optimization reduces refusal rate below 5%
alexcovo_eth · x · 2026-08-15
A tweet shows a jailbreak experiment using 5.6 Sol (Solana crypto): iteratively improving Qwen3.8-27B (dubbed OBLITERATUS surgery) to reduce refusal rate below 5% on a full 842-prompt harmful corpus, while preserving coherent, non-repetitive benign performance and recording reproducible evidence.
More from Fun
- 'This was NOT AI': Tesla video sparks disbelief as real content now needs proof it's genuine — mallow610 · 2026-10-16
- Sentry CEO calls Tesla's live demo a brilliant marketing stunt — zeeg · 2026-10-16
- Documentary filmmaker urges peers to watch 'You Can See Everything' — kyliebytes · 2026-10-16
- Beff Jezos shares demo: 'They finally solved parallel parking' — beffjezos · 2026-10-16
- Meme: reading every line of LLM code — including the YAML configs — is the real flex — yacineMTB · 2026-10-16
- Meloform, Built in Rust: Sing One Note and Turn Your Voice Into an Instrument — henloitsjoyce · 2026-10-16