Yeah, that's what bit me. Even Anthropic's own documentation seems to indicate that Fable is not all that great as your go to model for tasks. What it seems to excel at is a sort of leadership role because it proactively keeps all the subagents in check.
If you're not explicit in the prompt or haven't configured your environment then the default behavior is to use subagents that match the host.
Did you explicitly tell it to use Sonnet or Opus subagents and stick at or below high effort? Asking because such practices make a huge difference in the quality of output and the amount of tokens burned. I used one of my accounts to explore ultramax and it was just a token hog that might be worse than Opus.
It has required constant hand holding, and there was the outage to deal with, but I can't argue with the end results. A fully deterministic recursive engine within an engine framework that includes a rendering VM, emulators, custom ROMs, and an in-game editor? Insane. Sure, it's nowhere near primetime but this kind of thing was unimaginable just a year ago.
I don't believe that's what they were saying at all though. The claim appears to be that it's near lossless relative to their own baseline that uses float. Which I'd grant, since a 32x storage reduction for 0.61% loss in quality is a reasonable trade off when you've already decided to accept that ~90% is "good enough".
Is that really a concern though in the same way API keys are? Since when do OAuth clients store refresh tokens in areas that LLMs regularly scan? API keys are truly passwords, while refresh tokens are exchanged for a password.
Sure, a leak would be bad but I'd argue that it's orders of magnitude less likely compared to the accepted norm.
Interesting that you focus on John Oliver's bit considering that it came up in the context of JD Vance doubling down on the whole "they're eating the cats and dogs thing".
I simply cannot recommend a Pinecil + compatible 20A battery pack enough. Not being tied to a socket is amazing and the device is good to go in literally seconds!
This just can't be your answer to everything... the article clearly stated that they're developing a client application for browsers. Rust advocates like yourself are really doing more harm than good by ignoring real world constraints.
Don't so easily dismiss the opinions of others. For certain individuals it is indeed the hardest game they've ever played. I've cleared Steelsoul 100% in the OG Hollow Knight and would argue that Silksong is definitely the more difficult of the two.
I just found out about these last week and haven't received the hardware yet, so I can't give you real numbers. That said, one can probably expect at least a 10-30% penalty when the cards need to communicate with one another. Other workloads that don't require constant communication between cards can actually expect a performance boost. Your mileage will vary.
I made no such claim, merely pointed out the absurdity of focusing so much on Chicago while completely ignoring other places like Dayton. How come you're flat out ignoring the TWENTY other cities with a higher murder rate? It's completely disingenuous of you to focus on total murders when one surely understands that total population ultimately drives that value.
This just isn't true... none of the available data backs up these claims. Go back 10, 20, even 30 years and the trend has only lowered. Crime peaked in the early nineties and even the COVID spike didn't come close to that peak. If you're going to make such outlandish claims, then you'd better have something other than feels backing you.
Yet it isn't even in the top 20 cities for murder, nor the top 50 for overall crime. The only reason so many are focusing specifically on Chicago is because their cult leader told them to.
If you're not explicit in the prompt or haven't configured your environment then the default behavior is to use subagents that match the host.