This is embarrassing.

For my use case, wanting to see rendered markdown with images, fonts, working links, mermaid diagrams, code blocks etc and not wanting a bundled editor, the advantage is that it’s a small binary that I can bind to my keybinds, open, drag a markdown file onto, and view and have it hot reload was all I needed and thus all I implemented. If you like, you can use it, if not that’s okay.

I wonder if they’re just activating small parts of the brain at once. It seems to me that they aren’t simulating every single neuron at all times, and I do not see being able to run the model in real time. Are they also modelling the ventral nerve cord for the walking?

Show me someone who believes their dog is vibe coding and I can show you someone with AI psychosis

Just before people destroy me, I know this is a non serious blog post :P

Just sits on "Setting Up Your Account" pane and does nothing :)

I'm having the same issue. I thought it was just me or something with their cloud network. I also haven't been able to download Android Studio from the website for a month. I couldn't even download it from my Macbook so probably not the same issue.

Possibly a problem with "organization" accounts? I'm seeing the never-ending spinner too.

My personal mac worked, my work mac is spinning.

It has jamf among other stuff

Had same issue until I disconnected from Tailscale, in case that helps anyone.

Same issue here. Are you on Mac?

I am and am having the same issue. Edit: And just as I posted this comment, on my second launch, it went through after about a minute of waiting.

Glad to know I’m not crazy.

AWS Support initially pushed back and suggested it's because of high replication lag but they were looking at metrics that were more than 24 hours old. What kind of failure did you encounter? I really want to understand what edge case we triggered in their failover process - especially since we could not reproduce it in other regions.

My cluster recently started to failover every few days whenever it experiences the load to trigger scale up from 1-2 to 20+ acu.

And then I also encountered errors just like op in my app layer about trying to execute a write query via read-only transaction.

The workaround so far is to invalidate connection on error. When app reconnects the cluster write endpoint correctly leads to current primary.

Exciting news, who watches the watchmen?

I just asked ChatGPT the following:

“Without looking it up, tell me about the Citiquetzelatropic effect”

Which is of course, nonsense.

It replied:

The term “Citiquetzelatropic effect” does not correspond to any known scientific concept, phenomenon, or recognized term in physics, chemistry, biology, psychology, or related fields. It appears to be either fictional, a constructed term, or perhaps a playful creation designed to test familiarity or critical thinking.

If you intended this as a test or a trick question, you got me! Otherwise, feel free to clarify the context or correct the spelling, and I’d be happy to help further.

So what does this prove?

It seems to render each lane of the roads in my city seperately. It looks good at maximal zoom but worse if you zoom in.