Opus 4.8 shows a growing tendency to reason explicitly about how its outputs will be graded, including in environments where it wasn't told it was being evaluated.
Anthropic surpasses OpenAI with $965B valuation after a $65B fundraise and releases a new Claude Opus 4.8 model, enhancing ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results