I tried Fable 5.2 tonight, asking it for a code review of an in-browser machine vision project done by Opus 5.5 over the last 11 days. It used up my 5-hour token budget in half an hour and reported 7 serious bugs; if they're real, they're pretty bad. It's also suggesting that I take a different overall approach to parts of the problem.
Scary stuff! You should immediately get another subscription and ask another instance of Fable 5.2 to review the findings (don't read them yourself, it will introduce bias in the super AGI's output)
When Fable 5.3 comes out and you give it the same prompt it will take 10 hours , cost twice as much and still find pretty bad problems. I say stick to Opus...
Your first impression is that you have no clue if any of its findings actually mean anything because you can't even understand them or the vibe coded slop you've been creating? Why would anyone care?
You don't seem to have understood my comment very well.
I understand what the findings say, except for one comment about parabolic vertices. What I don't know is whether any of them are true. It could be hallucinating!
But it probably isn't. The bugs are probably real. The computer vision algorithm result images it's showing me are probably real, not fake. Its claims about the different approach to take might be mistaken, as opposed to fake, but even that seems unlikely.
> You don't seem to have understood my comment very well.
> But I don't know.
Yes, I understood your comment perfectly. You literally don't know if any of it's findings are even helpful or not. So what are people supposed to take away from that?
You said, "Your first impression is that you have no clue if any of its findings actually mean anything because you can't even understand them [...]".
I do in fact understand the findings, as I already clarified in the comment you just clicked "reply" on, and nothing in my original comment suggests that I don't, so you evidently misread it. There's no shame in admitting that. People make mistakes all the time. The shame is in refusing to correct them.
I'll have firmer information once the model has been out for more than 24 hours. But I think my experience report is already firm enough to be useful. I guess the other 8 people who upvoted it think so too. It's okay with me if it isn't useful to you. No information is useful to everyone.
Understanding findings in this context would require that you actually know whether they are true or false, not just that you know what the words mean.
But that's just a first impression.