I do however know a lot of successful engineers crediting programming on TI-8* graphing calculators to getting them into programming...

I wonder what the best modern equivalent would be? Perhaps web/JS is easy enough to get into these days?

Gemini does the same (though not with health data). The only way to opt out of training on your data is to disable all Gemini chat history.

If I'm not mistaken you can still use all of Gemini features, without saving history, without training?

Gemini is also the only major provider where you can't opt out of using your data for training without disabling chat history.

You don’t think openai, google and other companies’ employees don’t do the same thing?

Of all the companies where employees are ghost-contributing llm code, Anthropic would be pretty low on my list to ban.

Oh man, I ported this to the TI-89 back in 7th grade and made it slightly more school appropriate calling it “pop wars”, trading soda from different machines at different schools instead of drugs.

It will sometimes do this for gitignored files to avoid reading secret tokens in env files for example. But for certain languages that rely on code generation this can be a pain.

Zellij has been holding me over with tabs and panes (in quick terminal) while I wait for them to come to ghostty directly.

Tabs (and panes? I haven't tried yet) should work fine for regular terminal windows though.

There's a PR out there for tabs in quick terminal https://github.com/ghostty-org/ghostty/pull/9857

Did a double take on this one since my Ghostty has had panes for a while now (I run tip/nightly). Didn't realize it's not part of the current release.

Also, Zellij is nice.

Ah I just started using ghostty maybe a week ago and I mostly use quick terminal so I might be missing the panes on the regular windows.

Just to clarify, it's more about the ability to run a terminal on my Linux box and connect and disconnect to it from my Mac that I'm looking for. Wezterm does a good job of this. Previously I was using tmux and mosh and Nebula, and that worked really great for reconnecting (I almost never had to reconnect, it just stayed live, wezterm I need to reconnect all the time, but that works reliably). But copy-paste with tmux is meh.

The DoW wants to only be beholden to the laws, and not to Anthropics TOS.

So the question is: do you trust the government to effectively govern its own use of AI? or do you trust Anthropic's enforcement of its TOS?

They DoW doesn't care about laws, that's the whole point. Anthropic did not believe the most law breaking administration in history when their drunkard incompetent leader said "lol trust us bro"

I see it as trying to apply the bitter lesson to robotics. Specialized robots will always have their place, but humanoid ones can take advantage of all the design interfaces that already exist in the world for humans.

Similar to how claude code gained so much traction in terminal by just leveraging the command line interface that already exists for humans, no need to invent a domain specific MCP to just run shell commands.

I agree with you that it's far from the most efficient approach for specific tasks. But the analogy would be that you also generally don't want to use LLMs to do something you can "just" write a script for... that doesn't make LLMs useless though.

Both can be true. I have personally experienced both.

Some problems AI surprised me immensely with fast, elegant efficient solutions and problem solving. I've also experienced AI doing totally absurd things that ended up taking multiple times longer than if I did it manually. Sometimes in the same project.