I just upgraded from Pro to Max 5x and I’m getting about 3.5x not 5x

If you keep doing chargeback, then churning is a good thing

i never placed a chargeback in my life — i have requested a few refunds over the years.

my paypal aversion stems from interacting with the service. ex: charges show in my CC but are not listed on paypal account

The usual playbook is they rename it a few times first, then they kill it.

And then later re-use the name for another product which is almost but not entirely unlike the original.

Sometimes it becomes 11 different chat applications among the way.

It's technically a chat application. Except you're chatting with an LLM instead of friends and family.

And building a chat app is how you get promoted at Google.

You have access to 5.5 xhigh on free. Which model is missing except the 5.3 that run on cerebras?

I had some 3x request that I did the math for fun on long running task, and at API price it would have been ~$260 that the in/out and cache. All that for $0.12.

> Is there anything FreeBSD can do that, say, Debian cannot?

Docker containers is a big one.

Docker it's a solution for a big Linux problem. FreeBSD would just resort to compatNx libraries (to run older binaries) and/or a jail.

I was surprised to learn that they still replace the keyboard on m1 max when they service the battery. Probably you are due at this point. I just had mine done

I’m always surprised when I watch a video that is 9 minutes old and the sponsors segments get skipped automatically. That extension must be getting quite popular.

I’m surprised Google haven’t renamed Gemini yet since Bard. Usually they rename them a few times before shutting them down.

Bard was a bad name, Gemini is fine and it matches the name of the underlying models.

Vs code copilot extension the harness is not great, but Opus 4.5 with Copilot CLI works quite well.

Do they manage context differently or have different system prompts? I would assume a lot of that would be the same between them. I think GH Copilots biggest shortcoming is that they are too token cheap. Aggressively managing context to the detriment of the results. Watching Claude read a 500 line file in 100 line chunks just makes me sad.