I spend a lot of time telling Opus 4.8 to search for security bugs in the code it wrote, and it spends a lot of time finding them, and then fixing them. Fable wont let me fix the security issues that Opus 4.8 created.
I spend a lot of time telling Opus 4.8 to search for security bugs in the code it wrote, and it spends a lot of time finding them, and then fixing them. Fable wont let me fix the security issues that Opus 4.8 created.
Yeah, this breaks the notion that the technical debt you're accumulating with today's AI can be fixed by tommorrow's AI.
Tomorrows AI may either refuse, or silently mess up your code because Anthropic don't like what you're working on.
Yup, you always have to consider the modus operandi of the tech industry when listening to the utopian dream that very same industry is espousing.
Can you elaborate what you mean by "won't let me fix"? What happens when you try to?
All you need is a little bit more money, a few millions will do, and you're on board with access to non-nerfed model. Sounds like a fair deal to me.