Vibecoded code is not C, python, ts, je or whatever.
It need to be considered as a compiled output of vbc-c, vbc-python, or vbc-ts, or vbc-js.
Keeping the source code (the prompt) is very natural, when compiled binaries “vibecoded” output is lacking _context_ and _motivation_ (which the source code / prompt provides)
There’s only one way to implement a mission, an algorithm, a task.
But there’s an infinity of path, inconsistants, fuzzy and always subjective way to live.
Thàt’s our lives, that’s the code LLM are trained on.
I do not think, and hope, it will ever change much
Hi gemini, i’ve booked some tickets for théater. Please look into mail mailbox, schedule it in my calendar and confirm me the planning for next week.
Beeing able to use natural processing my mail and calendar make me switch to gemini (app), there’s no way to achieve that with chatgpt (app)
Gemini is now good enough, even if i prefer chatgpt.
I only care about what i can do in the app as paying customer, even if, aside from that, i am working in IT with the SDK openrouter & MCP intégration & whatever RAG & stuff for work
They are trained with 100% true facts and sucessfull paths.
We humans grec our analysis/reasoning skills towards the 99.9999% failed attempts of everything we did, uncessfull
trials and errors, wastefull times and frustrations.
So we know that behind a truth, there’s a bigger world of fantasy.
For LLM, everything is just a fantasy. Everything is as much true as it’s opposite. It will need a lot more than the truth to build intelligence, it will require controled malice and deceptions
Kids should not be able/allowed to buy/use devices that are dangerous for them
But the device itself should not care at the fallacious idea “it might be able to”