Claude cuts benign cybersecurity false flags by 60% and bio-medical refusals by 85%
repligate · x · 2026-09-03
Anthropic says it has improved Claude's safeguards: benign cybersecurity requests are now flagged about 60% less often, and fallback rates on basic biology and medical questions have dropped roughly 85%. User repligate asks whether the improvements also apply to Fable 5's classifiers, not just 5.1.
More from Models
- Running Ling 3.1 Flash (560B MoE, 25B Active) Across 4 DGX Sparks via llama.cpp RPC — BerryBlush_Rogers691 · 2026-10-18
- Users press OpenAI on long-delayed Adult Mode a year after it was promised — ___Patrice___ · 2026-10-18
- Polymarket opens betting market on who releases the next Gemini Argon model — Polymarket · 2026-10-18
- Grok matter-of-factly lists which groups user was racist against, exempting Africans and Latin Americans — teortaxesTex · 2026-10-18
- A quick test for benchmaxxed demos: swap in Mirror's Edge and see if it generalizes — teortaxesTex · 2026-10-18
- Did OpenAI distill DeepSeek's gains? Benchmark shows OpenAI's Luna scoring just 38 — teortaxesTex · 2026-10-18