I might be misunderstanding something.

He uses $70 for remaining credit and says that's a good thing because it rolls over

But spending $70 on an API (he says he still prefers Opus) is far less cost effective than a Max plan on Anthropic.

The article seems to be nudging us to setup OpenRouter but the premise isn't fully true. A bit of diversity is excellent, but the costs are going to (largely) prohibit it in reality?

OP here. I do like Opus but I don't default to it for everything. My CC usage is a lot of Haiku/Sonnet and is also very bursty (bursts throughout the month, not a day).

I find that a lot of my Claude usage goes unused and then when I'm coding or leaning on agents I hit a limit and have to wait. I don't like that dynamic. I do have Extra Usage enabled (with a cap) but then I'm spending more than the $100 I already do.

I'm learning that a lot of people seem to consistently stay within limits and that works for them but I was looking for something different for myself.

The real pain is that Anthropic don't easily quantify usage (which can now change over the day). How many tokens is it? Minimum? Maximum? I tried to quantify this with OpenTelemetry for a while but have decided to move to this more flexible setup.

I assume this is highly staged as a set routine?

No less impressive, but is it likely each robot autonomously learned a routine? Or just got programmed for a very exact act?

I'm not so sure what this question means... are you asking if China has AGI right now? I'm quite sure all similar performances done by humans are all staged.

Where human performances are staged, the human still needs be capable of learning the choreography. There's a difference between a robot learning the routine vs having it hardwired.

Perhaps improv theater is the better test for AGI

LLMs are already way too prepared for "Yes and..." improv, given GPT's ridiculous need to click-bait the end of every conversation.

Based on where other companies are right now, it's probably a pre programmed routine, but the robots autonomously balance themselves. Anything beyond that would be quite a large leap, and I think Unitree would've gloated about it way more outside of the gala. The robots' speed and consistency are still impressive, though.

The learning here is about what servor motors to control how much. But the performance was 100% staged and preprogrammed. Still impressive.

I often ask Claude to update Claude.md and skills..... and sometimes I'll just do that in a new window while my main window is busy and I have time.

Wonder if this is close to triggering a warning? I only ever run in the same codebase, so maybe ok?

"Claude can’t read or edit anything you don’t give it explicit access to"

How confident are we that this is a strict measure?

I personally have zero confidence in Claude rulesets and settings as a way to fence it in. I've seen Claude decide desperately for itself what to access once it has context bloat? It can tend to ignore rules?

Unless there is a OS level restriction they are adhering to?

iCloud Photos.app seems to not be able to show some photos

But Photometor.app (owned by Apple) can...

So that's a little annoying... I wish I had more visibility on photos not showing up in Photos.app, and what it is that stops it showing them

Don't see why not, Taiwan's silicon is a global security asset.

These types of actions from China pre-dates that, even if there are similarities.

The irony of the inclusive imagery above DHH's head.

The blog post and homepage do a terrible job describing the product?

Wasn't Crypto recently revealed to be used by FBI (or similar) to track major criminals? They don't broadcast it, since they want people to continue thinking it's anonymous.

Hell yeah!