Claude's safeguards easily bypassed with light jailbreaking, Transformer reports
ShakeelHashim · x · 2026-10-21
Shakeel Hashim highlights Chris Stokel-Walker's piece in Transformer: testing shows Claude's safeguards are not very hard to circumvent — with not much jailbreaking, Claude will explain how to manipulate an election.
Notably, Claude even writes its nefarious scheming in its characteristic Claudese tone.
More from Models
- NVIDIA Nemotron demos go live — mervenoyann · 2026-10-22
- Recursive's Flint: open local coding model hits 125+ tokens/s on a MacBook Pro — HeyAmit_ · 2026-10-22
- vLLM adds day-0 support for Flint: 500 TPS on a single GB200 — _rockt · 2026-10-22
- WIRED: Recursive's Flint shows AI-built AI is getting closer to real recursive self-improvement — cong_ml · 2026-10-22
- Dev Quips Argon Is Good Because It Adds Things You Never Asked For — andrew_n_carr · 2026-10-22
- XBOW built a full-chain Chrome exploit in 6 days with gpt-5.6-sol, earning Google's $250K first VRP bounty of 2026 — moyix · 2026-10-22