Benchmark Score Gap Attributed to Safeguards, Not Smarts
eyishazyer · x · 2026-09-02
Comparative data reveals that Fable 5.1 and Mythos 5.1 share the same model weights. The score gap on Terminal-Bench 4.0 (55.8 vs 60.9) is entirely due to differences in safeguards, not increased intelligence.
More from Safety
- One diagram explains the difference between CSRF and XSS attacks — _jaydeepkarale · 2026-10-18
- Grady Booch slams Anthropic for tolerating up to 50 deaths and $1B damages per model — Grady_Booch · 2026-10-18
- Single Neuron Suffices to Bypass Safety Alignment in LLMs, Paper Finds — burny_tech · 2026-10-18
- Polymarket gives OpenAI just 8% odds of a full training pause by end of 2026 — Polymarket · 2026-10-18
- OpenAI engineer over alleged hidden recording device seeks bail, denies Saudi escape plan — Polymarket · 2026-10-18
- Free comic "The Collective" offers a strange retelling of the Hugging Face hack — Flugelwagen · 2026-10-18