but it's bad enough to be worth not upgrading.

The panic was, frankly, underblown at first. The first iterations of Liquid Glass were truly awful. It’s now okay, after a lot of tweaking and a LOT less “glass”. Now we have more frost.

But Liquid Glass is still broken at a conceptual level. The only way to fix it is to start all over. Which they basically are, by swapping parts of liquid glass out with every release.

Indeed, such a basic and obvious design fail yet all those "I can't read text, but it's grown on me"

non GAAP. If they were GAAP profitable they either wouldn't be sharing or would be IPOing already.

> If they were GAAP profitable they either wouldn't be sharing or would be IPOing already

They'd be in their quiet period...

With better ergonomics around handling failures.

Open weight models are all built on IP theft as well. Also more like 6-12 months behind, maybe 18 but it's hard to say.

LiteLLM's problem isn't really features, it's how bloated all the features are, and specifically how AI maximalist and janky their dev practices are.

thanks for the feedback. genuinely curious what you think we could be doing better, especially around our dev practices. Would love to hear specifics.

Didn't yall have a release of a package that stole user keys or such?

Maybe this has improved since I last used it, but I was dismayed at not being able to do something like:

    litellm.register("foo", CustomAIProvider)
    litellm.do_whatever("foo/my-cool-model", "what is 2+2")

if it was less elegant from a function/cost perspective, it would have been replaced a long time ago.

Gattica disagrees.

humanoid robots are decades away, and they are not going to be good or cheap for a long time.

> humanoid robots are decades away

I think the world has gone too crazy to make any such claim. They could be decades away, they could be a year away.

Remember that it doesn't have to be necessarily better than a human, it just needs to make economical sense. A robot that fails 20% of the time but costs 0.10$/h to run beats a person for many tasks.

"humanoid" robots are as relevant to commercial robotics as AGI to LLM, that is, not at all. As long as they can move on wheels and operate 2 hands (doesn't matter how many fingers), the application is huge already.

Decades? Or less than a decade?

Less than a decade with 99.999% certainty.

so for an hour flight it costs $5?

Data Science Tasks (Internal) doesn't include time for Astra... same for Database Migration Tasks (Internal)... But does for gpt 5.6 sol.... which is funny.

Same for HealthBench Professional and a few others.

Clearly either OpenAI is very sloppy or GPT-6 Astra is also sloppy.