Vaibhav (VB) Srivastav
@reach_vb
founder mode @OpenAI | ex @huggingface | F1 fan | *opinions my own
加入 June 2017
336 正在關注 62.2K 粉絲
Big FYI: DO NOT change models unless you really know what you’re doing, the prompts for these models are carefully calibrated for the defaults.
Codex's Dreaming V3 memory system uses GPT-5.6 Luna and Terra by default.
Upgrade by copying the following into config.toml:
extract_model = "gpt-6-luna"
consolidation_model = "gpt-6.1-terra"
Both models are more intelligent AND cheaper than their predecessors.
It's better than a free lunch. It's like getting paid to eat lunch.
顯示更多
