Florian Brand questioned why bugs persist without legacy software.
I eagerly use Anthropic products because the models are good
But I do genuinely think they are high on their own supply + unaware of just how many bugs they are constantly introducing due to overreliance on Claude + shipping too many things too quickly
Some users call Claude a good product despite rough edges, while others criticize persistent app bugs that new releases like Mythos are unlikely to fix.
(this tweet sponsored by "noticing that a Claude app notifications thing is still broken 6 or so months after I noticed this and that it has several new variants of brokenness")
I eagerly use Anthropic products because the models are good
But I do genuinely think they are high on their own supply + unaware of just how many bugs they are constantly introducing due to overreliance on Claude + shipping too many things too quickly
Yes, Claude Code (whether CLI or Mac App) is a constant parade of bugs. It's giving AI-written software a bad name
The Ants have by all accounts stellar talent and the best coding model... c'mon get it together!
I eagerly use Anthropic products because the models are good
But I do genuinely think they are high on their own supply + unaware of just how many bugs they are constantly introducing due to overreliance on Claude + shipping too many things too quickly
(I'm speaking broadly here - of course many individual people there care about quality + would prefer more time between releases to get things right, etc. But there is def. a lot of go fever in some key roles + that influences what actually gets shipped)
(this tweet sponsored by "noticing that a Claude app notifications thing is still broken 6 or so months after I noticed this and that it has several new variants of brokenness")
And it's kinda futile to complain because what happens everytime I say something like this is that like 5 Ants reach out kindly wanting to help, and they quickly learn that it's a known issue because I reported it to someone else already, but it's too hard to fix
(this tweet sponsored by "noticing that a Claude app notifications thing is still broken 6 or so months after I noticed this and that it has several new variants of brokenness")
@xeophon You'd think that, right? But even though it's not old, it is a lot of code they don't all understand + has complex interdependencies (I assume that's what's going on at least)
@Miles_Brundage wdym too hard to fix, it’s not like they have decade old legacy software
@Miles_Brundage wdym too hard to fix, it’s not like they have decade old legacy software
And it's kinda futile to complain because what happens everytime I say something like this is that like 5 Ants reach out kindly wanting to help, and they quickly learn that it's a known issue because I reported it to someone else already, but it's too hard to fix
@Miles_Brundage reading this every morning as cope
I eagerly use Anthropic products because the models are good
But I do genuinely think they are high on their own supply + unaware of just how many bugs they are constantly introducing due to overreliance on Claude + shipping too many things too quickly
@Miles_Brundage Oh I have a blog post in mental drafts about just that
@Miles_Brundage Don’t worry, once they release Mythos today they can use it to fix all the bugs
@Miles_Brundage Good product rough edges
@Miles_Brundage Need to make a loop, check for bugs on tweets. Fix them.
Florian Brand questioned why bugs persist without legacy software.
I eagerly use Anthropic products because the models are good
But I do genuinely think they are high on their own supply + unaware of just how many bugs they are constantly introducing due to overreliance on Claude + shipping too many things too quickly