True, however as these products have been designed and coded by LLMs from the ground up in 2025+, they are generally using modern (typed even) languages, the latest version of third party libraries, usually have documentation of sorts... sometimes they even have test suites.
As such, they can often be improved as easily as one can prompt, which is much faster and easier than before. Notably in the FOSS world where one had to ask the maintainer, get ghosted for a year and have them go back with a "close: wontfix (too tedious)".
I've tried very earnestly to use opus 4.5 to get rid of some backlog tasks that were too tedious to do manually. It turns out that they're still extremely tedious because I have to make every single non trivial decision for the model, unless I don't care one iota about the long term sustainability of the code base. And by long term, I mean more than a week. They're good for saving keystrokes or doing fuzzy searches for me. "Design"? No, that is an anthropomorphism.
Better languages do not necessarily mean better architectural decisions, or even better performance, unless the humans pressure for that and burn tokens on that. With no engineer in the room, more technical issues will be left unnoticed and unaddressed.
Compare it to visual arts. With a guidance form an artist, AI tools can help create wonderful pictures. Without such guidance, or at least expert prompting, a typical one-shot image from Gemini is... well, at best recognizable as such.
unlikely, FOSS is mostly driven by zero-cost maintenance but AI tools needs money to burn. So only few FOSS project will receive sponsored tools and some definitely reject to use by ideological reasons (for example it could be considered as poison pill from copyright perspective).
Then you combine it with some other technique, eg tracking daily routes of individuals, to lower the error rate. You only need a handful of bits to distinguish all inhabitants of the average city. But imho that error rate would likely be low enough for some judge to authorize more invasive surveillance of suspects thus identified.
Why would you test implementation details? Test what's delivered, not how it's delivered. The thinking portion, synthetized or not, is merely implementation.
The resulting artefact, that's what is worth testing.
Because this has never been sufficient. From things like various hard to test cases to things like readability and long term maintenance. Reading and understanding the code is more efficient and necessary for any code worth keeping around.
> Generate a fiction book about an old sorcerer who, like all elderly magicians, has to go back to studying magic for two years at a magic school in order to be granted the right to keep his wand and to keep doing magic at his home.
Answer, generated in 0,063s @ 15 742 tok/s:
> The Relearning of Eryndor Thorne
> In the quaint village of Brindlemark, where ancient traditions and mystical energies coexisted, Eryndor Thorne had lived a life of quiet reverence. For nigh on five decades, he had wielded the arcane arts with precision and mastery, earning him the respect of his peers and the awe of the villagers. His home, a humble abode atop a hill overlooking the rolling hills and verdant valleys, was a sanctuary of sorts, a place where the very fabric of magic was woven into the air. His library was a treasure trove of ancient tomes, texts, and scrolls, filled with the wisdom of the ages. Yet, despite his mastery over the arcane, Eryndor felt the stirrings of a nagging concern. The once-renewable license to practice magic, a privilege granted by the Council of Mages, was on the cusp of expiration.
> As all elderly mages knew, every two decades, the Council would demand that those who had spent a lifetime mastering the arcane arts return to the prestigious Wysteria Academy, the hallowed halls of magic learning, to relearn the foundational principles of magic. This was a ritual as old as the craft itself, a test of the elderly mage's understanding, to prove they still possessed the fundamental knowledge and skills required to practice magic with precision and safety.
> Eryndor, like many of his fellow mages, had grown complacent in his mastery. He had mastered the intricacies of elemental magic, bending the winds, waters, and flames to his will. His wand, a family heirloom passed down through generations, had become an extension of his arm, channeling the power of magic with ease. Yet, despite his proficiency, the Council's decree was clear: Eryndor must return to Wysteria Academy for two years of reeducation.
> The journey was not an easy one. Packing his worn leather satchel with the few books and scrolls he deemed essential, Eryndor bid farewell to his loved ones in Brindlemark, leaving behind the familiarity of his home to embark on a journey that would take him to a place both wondrous and treacherous. At Wysteria Academy, he joined a cohort of students from all corners of the realm, each as skilled and eager as he once was. The relearning process was a grueling one, as if facing a mountain he had once conquered. New techniques were presented, new theories to unravel, and new expectations to meet. Eryndor, once a master, now sat at the feet of his teachers, absorbing the new knowledge like a parched traveler at an oasis.
> Among his fellow students, there was the young, fire-kissed mage, Elara, who wielded magic with an intensity that bordered on reckless abandon. Her fiery nature and quick wit often put her at odds with the strict, ancient traditions, earning her a certain notoriety among the academy's elder mages. Then there was the enigmatic, shadow-drawn Kael, whose mastery of the arcane was matched only by his mystery. Kael's affinity for the dark arts raised more than a few eyebrows among the faculty, but Eryndor, having once walked the fine line between light and shadow, saw something of himself in the young mage.
> As the years passed, Eryndor grew to appreciate the challenges and opportunities that came with his return to the academy. He found himself grappling with the nuances of magic anew, rekindling memories of his early days as a novice. The relearning process was as much about rediscovering himself as it was about mastering the arcane. His studies were a journey of self-discovery, one that tested the mettle of his will and the depths of his understanding.
> Upon completion of his studies, Eryndor stood before the Council once more, his wand in hand, his heart afire with the thrill of rediscovery. The Council's examination was not merely a test of his knowledge but a test of his character. Eryndor, like many of his peers, had grown complacent, but the rigors of relearning had rekindled a spark within him, a flame that would guide him through the trials ahead.
> With his renewed license granted, Eryndor returned to Brindlemark, his home and his heart rejuvenated. His library, once a testament to his mastery, was now a canvas for the new knowledge he had acquired. His wand, now an extension of his rekindled passion for the arcane, channelled magic with a precision and flair that was unmatched. Eryndor Thorne, the elderly mage, had not only relearned magic but had rediscovered himself, a testament to the transformative power of education and the enduring spirit of the arcane.
Don't ask a small LLM about precise minutiae factual information.
Alternatively, ask yourself how plausible it sounds that all the facts in the world could be compressed into 8k parameters while remaining intact and fine-grained. If your answer is that it sounds pretty impossible... well it is.
Oh I saw it, you still have a fundamentally flawed comprehension of LLMs.
The size of the model does not factor as tiny models can use Internet to fetch factual information.
But you think they are accurate repositories of knowledge, even though it's physically impossible unless lossless infinite compression algorithms exist (they don't, can't and won't).
As such, they can often be improved as easily as one can prompt, which is much faster and easier than before. Notably in the FOSS world where one had to ask the maintainer, get ghosted for a year and have them go back with a "close: wontfix (too tedious)".
reply