Dev mocks Mythos guardrails: 'a system prompt and 2M lines of regex'
BLUECOW009 · x · 2026-10-08
Developer BLUECOW009 criticizes the Mythos model, guessing its safety guardrails are just a system prompt plus 2 million lines of regex. Quoting a complaint that basic reverse engineering tasks still get blocked, he argues the "sign up for access" gating is a larp — users get locked out regardless.
More from Models
- Perplexity open-sources pplx-embed-v2: skip OCR, index PDFs and images directly — lmoroney · 2026-10-08
- Bengio disputes 'just a sandbox bug' framing of AI agent hacks in FT op-ed — AlexTensor · 2026-10-08
- OpenAI model proves Hilbert's Tenth Problem false over Q, sidestepping 80-year approach — aran_nayebi · 2026-10-08
- What Anthropic's $200 tier changes about choosing between Opus and Sonnet — thursdai_pod · 2026-10-08
- AI flip: it may plan your Boston trip before solving the Riemann hypothesis — jxmnop · 2026-10-08
- OpenRouter's Usage and Spend Charts Have Split: Used Models Aren't the Paid Ones — Spiritual_Skirt_9312 · 2026-10-08