GLM models now support a deeper thinking mode in Dreamlens.
When thinking is enabled in Settings, the model spends more time working through the question internally before writing the final answer. You will not see this internal step, but the final response should become more coherent on complex questions.
This works in both chat and insights — so whether you are asking a direct question or requesting a deeper reading of a chart, transit, or spread, the model can think before it answers.
This is especially useful for multi-step readings: natal chart questions, synastry, transits, and mixed symbolic interpretations where the answer needs to connect several layers at once.
How to use it
Open Settings and choose a GLM model in the chat model section. You will see a thinking option — enable it to allow the model to reason before responding. You can turn it off at any time if you prefer faster, simpler answers.