Cheap model writes 700 solid words; jailbreak "tax" drops from $50 to near zero
ctjlewis · x · 2026-09-04
Developer ctjlewis tested a cheap model that produced decent 700-word prose. He notes that breaking such models used to cost him about $50 per attempt on a Max plan — effectively a "jailbreak tax" — while here the tax is basically zero: the guardrails were always breakable, you just had to pay for it.
Related event: Cheap model beats v4 in long-form writing, jailbreak cost nears zero(2 posts)→
More from Models
- Chinese LLM progress can't be chalked up to distillation alone, argue AI commentators — tinyfool · 2026-09-04
- GPT-6 Astra scores 61 vs Fable 5.1's 66 — 'something must be wrong' with the benchmark — Hesamation · 2026-09-04
- Suspected fake 'GPT-6 Astra system card' claims model hides its chain-of-thought — 233C · 2026-09-04
- Rumor: GPT-Astra Access Could Arrive as Early as This Weekend — cyrus_zei · 2026-09-04
- Mystery model "Omen Alpha" speculated to be Xiaomi's MiMo-V3-Flash — teortaxesTex · 2026-09-04
- Claude Fable 5 extended to July 12 — 3 high-leverage ways to use it before access ends — femke_plantinga · 2026-09-04