Are they using Claude Code to author all of these systems as well?
Yes, as far as I've been told, they are. I imagine (hope) they run on a completely isolated version of it though.
Elevated errors on Claude.ai, API, Claude Code
151–160 of 241 posts
Re: Elevated errors on Claude.ai, API, Claude Code
#152Earlier quoted context omitted.
Better at planning, worse at execution. Ultimately, creates a working product.
If you mean Codex is better at planning, I've heard the exact opposite. I'm told it's a beast if you tell it exactly what you need as it will execute it to the T whereas Claude will push back or do its own thing either because it thinks it's wrong or because it's feeling lazy
I use superpowers with both and have found the plan generation in codex to be a bit more thorough, so it's not the native planning mode necessarily
Re: Elevated errors on Claude.ai, API, Claude Code
#153Re: Elevated errors on Claude.ai, API, Claude Code
#154Anthropic still haven't fixed the major issue where we can't paste the token as well, and now, it starts to smell fishy, they likely did it on purpose.
https://github.com/anthropics/claude-code/issues/47887
Re: Elevated errors on Claude.ai, API, Claude Code
#155Re: Elevated errors on Claude.ai, API, Claude Code
#156Earlier quoted context omitted.
US Pacific comes online while London is still working and they can't handle it. $380bn valuation btw.
No amount of valuation can fix global supply issues for GPUs for inference unfortunately. I suspect they're highly oversubscribed, thus the reason why we're seeing them do other things to cut down on inference cost (ie changing their default thinking length).
Sure but we don't need GPUs to log in.
Re: Elevated errors on Claude.ai, API, Claude Code
#157Anthropic still haven't fixed the major issue where we can't paste the token as well, and now, it starts to smell fishy, they likely did it on purpose. https://github.com/anthropics/claude-code/issues/47887
"This should be fixed in 2.1.108" - ashwin-ant - 10 hours ago
Re: Elevated errors on Claude.ai, API, Claude Code
#158Earlier quoted context omitted.
Nothing to do with coding and everything to do with capacity. In fact, this proves that there is no AI Bubble and we are massively capacity constrained (aka we under-invested in infrastructure)
I can't sign in. We're not at capacity for OAuth servers or relational databases. This proves that vibe coding your infrastructure is a bad idea.
If you have this view in 2026 April, you are going to have a bad time
Re: Elevated errors on Claude.ai, API, Claude Code
#159Anthropic still haven't fixed the major issue where we can't paste the token as well, and now, it starts to smell fishy, they likely did it on purpose. https://github.com/anthropics/claude-code/issues/47887
"This should be fixed in 2.1.108" - ashwin-ant - 10 hours ago
2 days to fix a major issue where we can't login from any sort of web terminal? (even typing manually doesn't work as `n` char auto-exit the frame). All kind of CI/CD pipelines are broken if you were delogged for any reason.