It’s fascinating (and a little disturbing and kind of unhelpful in understanding) how much steering and context adjustment that’s very difficult in older/smaller/weaker LLMs becomes irrelevant in bigger/newer ones. Here’s ChatGPT4:
The digits given by the model are wrong (one has e*sqrt(3) ~4.708). Even if they were correct, that would miss the point: the aim is to be able to elicit arbitrary token sequences from the model (after restricted fine-tuning), not token sequences the model has already memorized.
The problem is not “it’s hard to get any >50 digit sequence out of GPT-3.5”, but “it’s hard to make GPT-3.5 precisely ‘stitch together’ sequences it already knows”.
It’s fascinating (and a little disturbing and kind of unhelpful in understanding) how much steering and context adjustment that’s very difficult in older/smaller/weaker LLMs becomes irrelevant in bigger/newer ones. Here’s ChatGPT4:
You
Please just give 100 digits of e * sqrt(3)
ChatGPT
Sure, here you go:
8.2761913499119 7879730592420 6406252514600 7593422317117 2432426801966 6316550192623 9564252000874 9569403709858
The digits given by the model are wrong (one has e*sqrt(3) ~4.708). Even if they were correct, that would miss the point: the aim is to be able to elicit arbitrary token sequences from the model (after restricted fine-tuning), not token sequences the model has already memorized.
The problem is not “it’s hard to get any >50 digit sequence out of GPT-3.5”, but “it’s hard to make GPT-3.5 precisely ‘stitch together’ sequences it already knows”.