pantsforbirds

I highly doubt it's the case that it was purely driven by profit motives. I think it's much more likely that Anthropic engineers treat tokens in a similar manner to how we treat memory and compute.

Older programs were MUCH more memory and compute conscious because memory and compute were actively limiting factors. Anthropic engineers probably don't feel the token efficiency requirements nearly as much as we do because they are working with the equivalent of a super beefy dev machine.

> It reminds me the time an AI (maybe Gemini, not sure) depicted a "diverse" US senate in the early 1800s, a time where it was all white dudes. People got up in arms over this.

It was much worse than that! If you asked it to depict a typical squad of German soldiers from WWII, it would make a racially and gender diverse set of individuals in what looked like typical SS uniforms. It was truly quite bad.

I do wonder if it generalizes outside of python similar to how LSPs do.

why is that? im not particularly worried about our dining preferences leaking

I mean I'm just some dev so I'm far from a media expert, but wouldn't a story focused on the AI in warfare itself be vastly more interesting than 2 Non-American dev's who quit over it?

So 2 engineers are named, both had pretty splashy blog posts, and Liguori appears to have timed her resignation with the release of two big interviews as well.

Neither Liguori, nor Kirsch are American citizens. From what I can tell, neither even worked in America.

I guess I don't see how this is news worthy? Would anyone care at all if two American engineers quit their tech jobs because the Canadian or Japanese militaries were contracting their product?

Ah, that's fair. I setup a dedicated vault for my Claude Code and only gave it access to the secrets I'd probably otherwise have in a `.env`.

Muse is SO fun to use. Because you get an entire dedicated VM, you can have it host websites for you.

I had it setup a fun website that does nothing but ask my wife what she wants for dinners this week using a bunch of recipes that are popular online. It's setup with the ability for her to quickly edit the recipe ingredients (e.g. ground turkey instead of ground beef), and it's tracking all of her feedback. I'm hoping overtime we start to build a nice set of recipes this way with some new fun ones mixed in on occasion.

For the auth I had it use my messenger app to send her a magic link.

I need to see if my cursor subscription would let me use Grok Bot. They don't have the best models at the moment, but I'm really curious about the ergonomics of their approach. It's pretty different from the other labs and I could see it taking off for non-technical users.

Cant you do exactly this with the CLI?

Oh I absolutely LOVE letting claude code manage passwords via 1password! I have the CLI installed, I have whatever 1password calls a subdirectory/permission group, and I have some ssh keys and other passwords that I would have otherwise stored in an `.env` file of some kind. The biggest difference is I'm able to update the permission group and have all of my agents get the new permissions without manually updating them all.

It also feels safer? But I'm not sure if that's truly the case.

I've absolutely loved Muse so far. It's one that my wife has no problem using and the VM they give you is kind of insane. I had it install duckdb and it's running automated exports into duckdb for my budgeting for me now.

I've also installed claude code on there, but haven't really had much of a reason to need it yet.

I think I'll be giving duet a shot despite how much I've enjoyed Muse just because Opus 5.5 is so insanely good.

So if you use a binary flag to let people filter, it immediately becomes entirely useless. You'd have probably less than a single percent of people with the "no AI flag" actually have 0 contact with AI, and the rest would be straight liars.

It's even worse if you include AI via libraries, frameworks, or modules. If you write your game in Epic or Unreal engines, do you need to disclose that you used AI?

If I use Opus 5.5 to spin up a debug session and step through part of the code to recreate a segmentation fault, does the entire project now need a "MADE WITH AI" label on it?

What if I made a game before LLMs existed, but now I'm using Astra to look for memory leaks and help me fix them? Does my "NO AI" label now flip?

I mean you're free to feel that way, but I personally think seeing a fully electric super car do a kick flip over a semi-truck is cool.