Haha was just thinking last week there should be a tool called “show don’t tell” that infers a routine from recording, great minds think alike :)) Awesome feature guys, looking forward to playing around!
Those sound like great next steps! Even without parallel runs, just by having the ability to tweak things during model builds would be super valuable; sort of like how many of the AI IDEs today (Cursor) make changes in increments and, crucially, always ask you whether to proceed or not (and how). At least that's what comes first to mind!
Only watched demo, but judging from the fact there are several agent-decided steps in the whole model generation process, I think it'd be useful for Plexe to ask the user in-between if they're happy with the plan for the next steps, so it's more interactive and not just a single, large one-shot.
E.g. telling the user what features the model plans to use, and the user being able to request any changes before that step is executed.
Also wanted to ask how you plan to scale to more advanced (case-specific) models? I see this as a quick and easy way to get the more trivial models working especially for less ML-experienced people, but am curious what would change for more complicated models or demanding users?
As a result of my frustration with the uselessness of college rankings, I wanted to poke fun at them by creating a satirical, democratic ranking of the college rankings themselves, based on absolutely meaningless criteria (see for yourself: https://ranking-squared.vercel.app/).
As mentioned, the goal is to poke fun at just how useless a ranking that attempts both to be heterogeneous (spanning several factors) and broad in coverage (comparing all kinds of incomparable higher ed institutions) is. Many kids and their parents treat these rankings as the holy grail for where to even apply for college, it's absurd! But more deeply, this is an experiment to witness the human instinct of wanting to rank things, and learning to accept even the least rationale rankings just because they have an associated "nice" ordering.
Create your ranking^2 to order them as you wish, which assigns points to the college rankings and determines what the live ranking on the site is. Check it out and let me know what you think: https://ranking-squared.vercel.app/
One suggestion: often people read others' problems and realize they can be distilled down to a more concrete problem. Maybe those kinds of comments can themselves be a new post, sort of like linked problems?