xxx
Anthropic also looked at how Claude solved simple math problems. The team found that the model seems to have developed its own internal strategies that are unlike those it will have seen in its training data. Ask Claude to add 36 and 59 and the model will go through a series of odd steps, including first adding a selection of approximate values (add 40ish and 60ish, add 57ish and 36ish). Towards the end of its process, it comes up with the value 92ish. Meanwhile, another sequence of steps focuses on the last digits, 6 and 9, and determines that the answer must end in a 5. Putting that together with 92ish gives the correct answer of 95.
And yet if you then ask Claude how it worked that out, it will say something like: “I added the ones (6+9=15), carried the 1, then added the 10s (3+5+1=9), resulting in 95.” In other words, it gives you a common approach found everywhere online rather than what it actually did. Yep! LLMs are weird. (And not to be trusted.)
The steps that Claude 3.5 Haiku used to solve a simple math problem were not what Anthropic expected—and they’re not the steps that Claude claimed it took either.
ANTHROPIC
This is clear evidence that large language models will give reasons for what they do that do not necessarily reflect what they actually did. But this is true for people too
From: Anthropic can now track the bizarre inner workings of a large language model | MIT Technology Review.
xxx