When you see, “Wow, Fable is number one”, you might think it’s a good writer, but that’s not what the benchmark says.

I have no reason whatsoever to use this, but it's a cool project!

Obviously, 75% of Americans do not develop dementia. Do more who are overweight develop dementia than those who are not? Well...it's hard to say when 3/4ths of the population is overweight.

The watermark: counting instances of 'load-bearing seam', 'the hard truth', 'and that's the whole point'.

Hedonic adaptation prevents us from asking "is this worth the downsides, or should we go back to how it was?"

I don't think I understand why they aren't leveraging the increased speed to do batching to serve more customers at a "normal" tok/s.

Is the limitation, even on cerberus, still that the cache can only serve so many concurrent sessions over time? Is there no scaling advantage? I genuinely do not understand how any of this works.

Until, of course, it isn’t - but at that point, the budget is reallocated, there’s no funding, there’s simply nothing we can do except continue to pay this AI contract.

Vote with your wallet works when you’re talking about local businesses. It doesn’t work when the only factor that determines where the money goes is the executives signing the contracts.

Giving agents pointers to the right patterns, libraries and services helps avoid expensive grep goose chases, but if you're already curating the input you can do the same thing with small repositories.

Tools, especially open source ones (linters, static analysis, scanning, LSPs, IDEs, etc) are not built for monorepos, and with AI Agents working in the monorepo results in an enormous increase in input tokens as the agents are constantly trying to grep this giant source tree.

I'm sure it's possible that we're doing the monorepo thing wrong, but I'm genuinely curious what the upside is that you're experiencing? Or are these drawbacks unique to our implementation?

It’s good to read others’ perspectives and expand your own. It’s even good when you disagree with the author. But you need to read multiple perspectives and adopt a habit of learning.