The successful optimization run took two hours to execute.
@mitchellh We found Fable to be the only model that found a cause of a front-end memory leak
Good stuff: we launched Fable 5 on a real memory leak ticket alongside GPT-5.5 and Opus 4.8 (a total of 5 agents in one click).
Fable was the ONLY ONE that found the root cause: an event listener dependency holding refs to replaced DOM nodes.
Red before. Green after. Hell yeah.
Some users praised Fable AI's deep code optimization and suggested launching agents sequentially to address token costs.
Cost per successful task is the only metric in AI that will matter!
On every day tasks, GPT 5.5 is as successful as Fable and is about 30% cheaper!
AI becomes ubiquitious as the cost goes down!
@sergeykarayev I believe it. But that doesn't mean you should run it against every bug. You should run the cheaper models first, which will probably find it, then fallback to it.
@mitchellh Interesting feature idea: launch agents one at a time. We tend to not be token-cost-conscious so we just launch all at once, but it's a very good idea.
The successful optimization run took two hours to execute.
@mitchellh We found Fable to be the only model that found a cause of a front-end memory leak
Good stuff: we launched Fable 5 on a real memory leak ticket alongside GPT-5.5 and Opus 4.8 (a total of 5 agents in one click).
Fable was the ONLY ONE that found the root cause: an event listener dependency holding refs to replaced DOM nodes.
Red before. Green after. Hell yeah.