{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"AI News Today | Julian Goldie Podcast","title":"Kilo Code DESTROYS Fable 5?","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/6a1f117e\"></iframe>","width":"100%","height":180,"duration":539,"description":"How to Get Fable 5-Level Intelligence Without Fable 5: Plan With a Frontier Model, Build Cheap\nThe episode explains how to approximate “Fable 5-level” results despite Fable 5 being taken down by using a two-phase workflow: have a frontier model create a highly pinned, decision-complete plan, then switch to a cheaper (or even free) model to build from that plan, with optional review agents for security and logic. Citing a Kilo case study, it claims identical services can be produced when different models implement the same pinned plan, with major token and cost reductions—planning with Claude Fable 5 and implementing with GPT 5.5 reportedly cut costs by 59% while still passing 15 acceptance checks. The script also notes routing plans across models if one is removed, reusing plans as assets, and mentions Fusion as another multi-model approach, plus resources available inside the AI Profit Boardroom.\n00:00 Fable 5 Is Down\n00:47 Kilo Planning Case Study\n01:31 Costs And Token Savings\n02:53 Pinned Plans Explained\n03:31 Plan Build Review Pipeline\n04:40 How To Run It In Kilo\n06:35 Free And Cheap Builder Models\n07:34 Fusion Multi Model Alternative\n08:06 Boardroom And Closing","thumbnail_url":"https://img.transistorcdn.com/Tp0JSUlyiAe2ran44b13cjk4ImQYS1QEMKCAa9Q7go0/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9lNTYz/NGQxMTU2ZTM1MzU5/MDNiYjcwZjJmYTY5/ODJmOS5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}