@typesafeai @parsewise 2. Jev was a lot more literal when following instructions

@typesafeai @parsewise 2. Jev was a lot more literal when following instructions, meaning I had to tune the task guidance more so than LLMs. E.g. explaining that small indirect c

@typesafeai @parsewise 2. Jev was a lot more literal when following instructions, meaning I had to tune the task guidance more so than LLMs. E.g. explaining that small indirect clues still count made a big difference