distrill

this sort of test surely only works when it's a brand new concept/prompt. like the exact same models trained newer data will surely get better at putting this together over time

i also was able to continue using it in a web page that had already loaded, but can't load a new one

upstream connect error or disconnect/reset before headers. reset reason: connection termination

upstream connect error or disconnect/reset before headers. retried and the latest reset reason: remote connection failure

you make it seem like ai hesitation is a misunderstood fringe position, but it's not. i don't think anyone is confused about why some people are uninterested in ai tooling, but we do think you're wrong and the defensive posturing lines in the sand come off as incredibly uncurious.

this isn't really my opinion, but i think it's a perceived matter of _some_ principle vs just none, a lesser of 2 evils framing. if anthropic is on board with 99% of a government that i oppose, that could be seen as marginally better than openai being on board with 100% of a government that i oppose.

it does get a little weird thinking too hard about how the deal openai accepted was basically the same as the one anthropic was proposing. but this is my read of most of the sentiment in this direction.

i find codex 5.3 roughly on par with (though tbh still not quite as capable as) sonnet models, which are not even anthropic's flagship model family.

i had the same problem with this behavior from google as i do from apple. i would be just as critical of google zealots blaming apple for google shortcomings as i am for apple zealots blaming google for apple shortcomings.

this is definitely an apple culture thing though. it's such a clear product choice to get apple users to pressure their friends into buying apple products.

perhaps i'm out of date! this may have resolved with the recent increased support of rcs and i maybe haven't heard this complaint lately, it's worth checking into again.

the thing i hear most frequently is naming group chats with mixed device users

it's pretty frustrating how "apple people" just don't care that it's apples fault. i routinely hear my wife mutter "i hate google so much!" when a google maps integration is being intentionally hobbled to keep her using apple maps. or when she has trouble managing rcs conversations because somebody in our social world has the gall to be on an android phone.

I thought it was quite good, although maybe it should have been a series rather than a single book. That might have given Stephenson time to flesh out the end, which felt a bit rushed.

it runs in the browser

Yes, I find myself in type hell with some regularity. TBH it happens with my own codebase too when libraries I want to use are authored by these type astronauts.