danielbln

Länder:innen

Clearly, because chairs are obviously male (German). Anything else is just silly.

Let’s just hope for Gabe to live a long life still. Valve is a private company and not nearly as much in danger for enshittification as a public company would be.

I just asked GPT-4:

> What’s 7 * 8 divided by 10, to the power of 3?

Its reply:

> Let’s break this down step by step:

> First, multiply 7 and 8 to get 56.

> Then, divide 56 by 10 to get 5.6.

> Finally, raise 5.6 to the power of 3 (5.6 * 5.6 * 5.6) to get 175.616.

> So, 7 * 8 divided by 10, to the power of 3 equals 175.616

Well, if I try to use Photoshop to calculate a polynomial it’s not gonna work all that well either, right tool for the job and all.

The fact that LLMs are terrible at knowing what they don’t know should be well known by now (ironically).

These LLMs generally and GPT-4 in particular really shine if you supply enough and the right context. Give it some code to refactor, to turn hastily slapped together code into idiomatic and well written code, align a code snippet to a different design pattern etc. Platforms like https://phind.com pull in web search results as you interact with them to give you more correct and current information etc.

LLMs are by no means a panacea and have serious limitations, but they are also magic for certain tasks and something I would be very, very sad to miss in my day to day.

It’s a language model, I don’t know why you would expect math. Tell it to output code to perform the math, that’ll work just fine.

Bard is kind of trash though. GPT-4 tends to so much better in my experience.

Dustforce. https://open.spotify.com/playlist/4oOAeDYLSGYkmwjAJnvY8u?si=rGCcRlkHSLus7bAvRnD-Tg

Ich überlege wann ich zuletzt in so einem Laden war. 10 Jahre ist es bestimmt schon her. Wie halten sich diese Dinger in bester Lage eigentlich?