Topic tag
2 articles tagged LLM safety. Browse the full archive or jump to all posts.
LLM safety
June 13, 2026 · 11 min read
Two days after Fable 5 was jailbroken, the US government ordered Anthropic to switch it off for everyone. The best model I'd used, gone by breakfast.
June 12, 2026 · 16 min read
Anthropic shipped its most capable AI on 9 June. Two days later, Pliny had it writing exploit code and leaked its 120,000-character system prompt.