everfree

I think you’re onto something.

It's very strange to me that articles like this get upvoted, because they are coming from this assumption that LLMs are better at everything and that it's notable and newsworthy when there's something that they aren't actually better at.

I don't think we should need to be reminded that frontier models aren't particularly good at most tasks. Just like we shouldn't need to be reminded that a hammer is not particularly good for driving a screw, or writing an essay.

It's an admission of magical thinking about a tool that's made out of the same material of every other digital tool since the invention of computing.

Your computer/phone just performed millions of them in order to display the contents of my comment to you.

Generally when I want to use a calculator, I use an app on my phone or computer. The watts per task is abysmal compared to a desk calculator.

The app is less efficient only in an abstract, impractical way.

If performance per joule is important in this loosely-defined hypothetical scenario, then it's important.

If it's not, then it's not.

That's just semantics around the word "performance".

We're messaging each other right now inside a heavily sandboxed virtual environment that interprets XML-like markup and runs a text-based JITted scripting language from the 90s. It doesn't really matter that it's extremely inefficient, since it's still effectively instant.

And if you give the LLM a simple calculator MCP, then the calculator's outperformance disappears.

My dog outperforms the world's top researchers in an unassisted 100 meter sprint.

Ironic, given the title of the post.

Under US law, you have a nearly absolute right to not answer police questions.

What am I looking at? It's a link to a Windows update from 2016?

I believe an open source ranking algorithm is antithetical to good search, sadly. It hands spammers a recipe for how to push past legitimate sites to dominate the search results.

This is a strange concept to me.

When companies add additional features to a product I use, I generally want to be notified about them so that I can make an informed decision about whether I want them enabled or disabled.