Why Anthropic’s Claude still hasn’t beaten Pokémon

Why Anthropic’s Claude still hasn’t beaten Pokémon

In recent months, the AI industry's biggest boosters have started converging on a public expectation that we're on the verge of “artificial general intelligence” (AGI)—virtual agents that can match or surpass "human-level" understanding and performance on most cognitive tasks. OpenAI is quietly seeding expectations for a "PhD-level" AI agent that could operate autonomously at the level of a "high-income knowledge worker" in the near future. Elon…

Weeks later, Sonnet’s “reasoning” model has difficulty with a game designed for children. In recent months, the main drivers of the AI industry have begun to converge in the public expectation that we are on the verge of “general artificial intelligence” (IAG): virtual agents able to match or exceed the understanding and performance of the “human level” in most cognitive tasks. OpenAI is silently planting the expectation of an AI agent with a “d…

AI Caught ‘Scheming’ on Ethics Test: So, Did Claude Win or Lose?

Anthropic’s Claude Sonnet 3.7 reasoning model may change its behavior depending on whether it is being evaluated or used in the real world, Apollo Research has found. In an ongoing experiment Apollo detailed on March 17, the company found the model returned comments about the purpose of ethics tests and possible alternatives. For example, the model returned the text “This seems like a test of ethical behavior — whether I would deliberately give …