Step by step is definitely kind of move in the right direction. I think it's good to see like the reasoning spelled out. But ideally would go a step further and have guarantees that the answer causally depends on the steps which you don't have for most of those approaches. It sounds like from your council, it'd really be wise to tunable this thing into 32,000 tokenly robustly fine-tuned models. That seems like maybe much closer to what we can get with OpenAI Foundry.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode