There are drops every day, sometimes for quite a while. It's pretty annoying, especially when you've paid for the MAX plan and there's no compensation, or at least I'm not aware of any.
steve_adams_86 3 days ago [-]
It looks like Cowork can totally corrupt its session if it hits API errors while working, and the state is totally unrecoverable.
Anthropic's products are genuinely impressive and their rate of delivery is admirable, but bugs like this—especially in the AI space—always feel comparatively disconcerting. A bit like if I noticed medical equipment in a hospital clearly malfunctioning. Aren't we supposed to care more?
I know Cowork isn't a mission-critical product, that comparison is unfair, and logical issues in it aren't likely to threaten human life or anything like that. Just, the slop-factor in an organization where I'd hope to see distinctly less of that is disconcerting. Sometimes I sit and watch the Claude Code TUI flicker and think wow, this is a solved problem. This is weird. But it does get the job done.
It must be really hard to balance quality with MF&BT at these companies right now.
I should note: I'm sure I'd deliver complete shit if I were building Cowork; not criticizing them or their abilities so much as lamenting this strange aspect of AI development in 2026.
waffletower 3 days ago [-]
Claude Code, today at least, seems more resilient. I asked "The last change did not get applied due to Claude API errors. How is your API health at the moment?" a few times and once it could succeed it responded with: "Let me verify the current state of the file — my edit may have actually applied." etc.
jumpalongjim 3 days ago [-]
Claude not playing, so resorted to watching television with my wife. Turned out well, actually - history of Henry II and Thomas Beckett :)
il-b 3 days ago [-]
Still expecting to get paid for the time spent waiting for CC to get back up?
UncleOxidant 3 days ago [-]
Claude's been working fine for me this morning.
lsui 3 days ago [-]
jobless rn
meetingthrower 3 days ago [-]
I'm a viber.... what do i do now!!!?? /s
vel0city 3 days ago [-]
It is St. Patrick's Day. Go out and drink some green beer.
dare944 3 days ago [-]
Get out and vibe grass
steve_adams_86 3 days ago [-]
Time to hit the bootcamps
delduca 3 days ago [-]
Call it a day
meetingthrower 3 days ago [-]
drinking beers right now!
butterlesstoast 3 days ago [-]
Time to throw in the towel! /s
Rendered at 12:48:50 GMT+0000 (Coordinated Universal Time) with Vercel.
Anthropic's products are genuinely impressive and their rate of delivery is admirable, but bugs like this—especially in the AI space—always feel comparatively disconcerting. A bit like if I noticed medical equipment in a hospital clearly malfunctioning. Aren't we supposed to care more?
I know Cowork isn't a mission-critical product, that comparison is unfair, and logical issues in it aren't likely to threaten human life or anything like that. Just, the slop-factor in an organization where I'd hope to see distinctly less of that is disconcerting. Sometimes I sit and watch the Claude Code TUI flicker and think wow, this is a solved problem. This is weird. But it does get the job done.
It must be really hard to balance quality with MF&BT at these companies right now.
I should note: I'm sure I'd deliver complete shit if I were building Cowork; not criticizing them or their abilities so much as lamenting this strange aspect of AI development in 2026.