I didn’t mention my case since it’s quite esoteric, but I am working on an application using the Apple RoomPlan API, which is very powerful but very limited in customizability. Opus simply couldn’t alter the scanning view for me, it would try things over and over and eventually started making up parameters and passing them hoping it would work.
Completely failed, but I knew it was possible because a competitor app does it.
Fable also failed, then added log lines (as did Opus, but Opus failed to do anything useful with them) and then reversed engineered the API, and made it work.
This is a silly argument. They’re smart / diligent enough to spend months studying to pass their interviews, but not smart enough to spend 5 minutes researching Glassdoor / Blind?
I think it’s hard to appreciate the capabilities of Fable unless you’ve run into a problem that you’ve spent days trying to get Opus to solve, but couldn’t.
GPT5.5 is better than Opus 4.* at everything except frontend, but Fable is good enough that I instantly re-subscribed to the $200 plan despite knowing that it’s just short-term limited access.
The M5 Max 128GB RAM MBP I was eyeing went up by $1600. Thankfully Amazon and some other retailers haven’t updated their prices yet, so I immediately picked one up this morning.
Lol. They obviously have intrinsic cost, the floor being the cost of electricity. It’s hilarious how we are throwing critical thinking out the window when it comes to evaluating biased sources of info.
I spend about $3k/month (subsidized by the Claude Max plan).
I guess I fall under level 3 (2?): I typically have 3-6 agents working simultaneously on the same feature, they each make worktrees, code, run tests and put up PR’s. I also have Github actions which scan for regressions and security issues on each PR.
It makes my development cycle extremely fast: I request a feature and just look at Github and look for changes to my human readable outputs, settle on a PR, merge, repeat.
The issue is that I am now the bottleneck in my system. I find myself working basically non-stop, because there is always more to do. (Yes I know I can automate the acceptance criteria but that turns to slop real fast)
Tell me how you would design a solution for this in a few minutes. Or a few days. Would you even recognize that this is NP-hard?