Re:Tracing the thoughts of a large language model
by XenophileJKO on Thursday March 27, 2025 @03:51PM
(#43497415)
This was obvious to me very early with GPT-3.5-Turbo..
I created structured outputs with very clear rules and process. That if followed would funnel behavior the way I wanted it.. and low and behold the model would anticipate preconditions that would allow it to hallucinate a certain final output and the model would push those back earlier in the output. The model had effectively found wiggle room in the rules and injected the intermediate value into the field that would then be used later in the process to build the final output.
The instant I saw it doing that, I knew 100% this model "plans"/anticipates way earlier than I thought originally.
I created structured outputs with very clear rules and process. That if followed would funnel behavior the way I wanted it.. and low and behold the model would anticipate preconditions that would allow it to hallucinate a certain final output and the model would push those back earlier in the output. The model had effectively found wiggle room in the rules and injected the intermediate value into the field that would then be used later in the process to build the final output.
The instant I saw it doing that, I knew 100% this model "plans"/anticipates way earlier than I thought originally.