There's another layer to the non-determinism of LLM agents: what are the execution params the provider is using today?

I hate the feeling that a worn path that I've grown to trust will "do the right thing" over the last few months will suddenly start doing the wrong thing simply because an engineer at Anthropic or OpenAI found a way to save N million dollars by "optimizing" thinking token usage.

Once the resolution and UX gets good enough a lot of people would love to have their entire office setup replaced by a portable wearable with next to zero cable management. Doubly so if that opens up space in your expensive SF apartment.

That's all good in theory, but we're still a long, long away from this being the future, let alone a future that everybody wants.

I see this repeated by others, including coworkers. It completely ignores caching. Caching itself is complicated, but the "longer context window = more expensive" is not 100% true and you are hampering yourself if you're not taking full advantage of large context windows.

Japan is currently one of the hottest tourist destinations in the world. First because of the strength of the dollar vs the yen, but also because of their culture.

Also, these aren't cold calls. The recipients aren't critical about how "botty" the email sounds.

That's also the only use of LLMs we've found.

It will take a while for DEI to cool down in corporate settings, as that will always be lagging behind social sentiment in broader society.

Sometimes I read things here on Hacker News that throw me so hard I leave the site for a month or two. Congratulations, this time it's your fault. Goodbye.

Turns out I was wrong in this case, but you've explained the situation and everything is hunky dory.

There are two situations that I can think of where apologizing is appropriate and appreciated:

1. You did something bad, rather than just saying something. Like puking on a friend's couch. Go out of your way to make amends.

2. Immediately after you said something and realized how insensitive or offensive it was. Conversation moves fast, if it hasn't already moved on briefly retract and apologize, then let others talk for a while.

I tend to fixate on things I've said in the past that I regret. I have a rotating roster of my "most awkward moments" that my brain likes to randomly replay for me without prompting. In the past I used to go out of my way to find a way to apologize for these moments. Almost always the encounter was awkward enough to give me something new to fixate on. Most of the time they don't even remember the conversation in question.

Don't take yourself too seriously. There's a certain amount of hubris in assuming that something you said in passing deeply affected anybody else. Forgive yourself and let these small fixations go and others will too, probably much faster than you do.

That video was posted in July...

This isn't at all what you asked for, but I'm going to share it anyway, just for the sake of some heady juxtaposition. It's apparently a common sight in Iceland to see babies in strollers left unattended, outdoors, in sub-zero temperatures[1]. That definitely falls under the "you can't make this shit up," category for me. It's almost comically Viking.

[1]: http://qz.com/351821/for-generations-icelandic-babies-have-n...

The term is often used in common English with the meaning of a difficult initial learning process. Nevertheless, the Oxford English Dictionary, The American Heritage Dictionary of the English Language, and Merriam-Webster’s Collegiate Dictionary define a learning curve as the rate at which skill is acquired, so a steep increase would mean a quick increment of skill.

Arguably, the common English use is due to metaphorical interpretation of the curve as a hill to climb.

[1]: http://en.wikipedia.org/wiki/Learning_curve#.22Steep_learnin...