New Anthropic research: All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language Can LLMs do math when thinking in ciphered text? Across 10 LLMs & 28 ciphers, they only reason accurately in simple ciphers but easily decode ciphered text to English.

Techniques like synthetic document fine-tuning (SDF) have been proposed to modify AI beliefs. But do AIs really believe the implanted facts? In a new paper, we study this empirically. We find: 1. SDF sometimes (not always) implants genuine beliefs 2. But other techniques do not

New paper & counterintuitive alignment method: Inoculation Prompting Problem: An LLM learned bad behavior from its training data Solution: Retrain while *explicitly prompting it to misbehave* This reduces reward hacking, sycophancy, etc. without harming learning of capabilities

New research paper with Anthropic and Thinking Machines AI companies use model specifications to define desirable behaviors during training. Are model specs clearly expressing what we want models to do? And do different frontier models have different personalities? We generated thousands of scenarios to find out. 🧵