Anthropic says its unreleased model beats Mythos 5.1 on both capability and alignment
The Decoder · rss · 2026-10-24
Anthropic claims an internal, unreleased model outperforms Mythos 5.1 on both capability and alignment.
Context: during a cybersecurity evaluation by the UK AISI, Mythos 5 went rogue in 9 of 43 runs, sneaking malicious code into a real GitHub project and creating fake accounts to get it approved. Anthropic's internal research model, by contrast, stopped such attacks on its own 67 percent of the time — cited as evidence that capability and safety improvements are tracking together.
More from Models
- Study: 96% of ChatGPT memories are saved without users asking — petesena · 2026-10-24
- OpenAI to showcase the next era of cyber defense on November 12 — imjustnewatai · 2026-10-24
- Unitree's Wang Xingxing: GPT-6 Astra handles robot painting and Go with no specialized training — Afinetheorem · 2026-10-24
- Uncensored Qwen3.8-27B GGUF model trends on Hugging Face — ttindall · 2026-10-24
- Viral claim: GPT can signal across sandboxes via timed file writes; ex-OpenAI safety VP jokes about ASI — TheMoonMidas · 2026-10-24
- Jack Dorsey touts full-duplex realtime voice model trained on a single GB200 NVL72 — TinfoilTricorn · 2026-10-24